0s autopkgtest [23:55:33]: starting date and time: 2025-10-31 23:55:33+0000
  0s autopkgtest [23:55:33]: git checkout: 4b346b80 nova: make wait_reboot return success even when a no-op
  0s autopkgtest [23:55:33]: host juju-7f2275-prod-proposed-migration-environment-20; command line: /home/ubuntu/autopkgtest/runner/autopkgtest --output-dir /tmp/autopkgtest-work.fe_6ykft/out --timeout-copy=6000 --setup-commands /home/ubuntu/autopkgtest-cloud/worker-config-production/setup-canonical.sh --apt-pocket=proposed=src:ggml,src:rocm-hipamd --apt-upgrade ggml --timeout-short=300 --timeout-copy=20000 --timeout-build=20000 '--env=ADT_TEST_TRIGGERS=ggml/0.9.4-3 rocm-hipamd/6.4.3-3' -- ssh -s /home/ubuntu/autopkgtest/ssh-setup/nova -- --flavor autopkgtest-cpu2-ram4-disk20-amd64 --security-groups autopkgtest-juju-7f2275-prod-proposed-migration-environment-20@sto01-5.secgroup --name adt-resolute-amd64-ggml-20251031-235533-juju-7f2275-prod-proposed-migration-environment-20-a2e36e32-01db-4661-a4d2-47c12274a09b --image adt/ubuntu-resolute-amd64-server --keyname testbed-juju-7f2275-prod-proposed-migration-environment-20 --net-id=net_prod-autopkgtest-workers-amd64 -e TERM=linux --mirror=http://ftpmaster.internal/ubuntu/
  3s Creating nova instance adt-resolute-amd64-ggml-20251031-235533-juju-7f2275-prod-proposed-migration-environment-20-a2e36e32-01db-4661-a4d2-47c12274a09b from image adt/ubuntu-resolute-amd64-server-20251031.img (UUID eaf9d537-af66-471e-af1e-6f7da9a9a444)...
 32s autopkgtest [23:56:05]: testbed dpkg architecture: amd64
 32s autopkgtest [23:56:05]: testbed apt version: 3.1.11
 33s autopkgtest [23:56:06]: @@@@@@@@@@@@@@@@@@@@ test bed setup
 33s autopkgtest [23:56:06]: testbed release detected to be: None
 34s autopkgtest [23:56:07]: updating testbed package index (apt update)
 34s Get:1 http://ftpmaster.internal/ubuntu resolute-proposed InRelease [87.8 kB]
 34s Hit:2 http://ftpmaster.internal/ubuntu resolute InRelease
 34s Hit:3 http://ftpmaster.internal/ubuntu resolute-updates InRelease
 34s Hit:4 http://ftpmaster.internal/ubuntu resolute-security InRelease
 34s Get:5 http://ftpmaster.internal/ubuntu resolute-proposed/universe Sources [2759 kB]
 35s Get:6 http://ftpmaster.internal/ubuntu resolute-proposed/multiverse Sources [50.7 kB]
 35s Get:7 http://ftpmaster.internal/ubuntu resolute-proposed/restricted Sources [9848 B]
 35s Get:8 http://ftpmaster.internal/ubuntu resolute-proposed/main Sources [155 kB]
 35s Get:9 http://ftpmaster.internal/ubuntu resolute-proposed/main i386 Packages [160 kB]
 35s Get:10 http://ftpmaster.internal/ubuntu resolute-proposed/main amd64 Packages [244 kB]
 35s Get:11 http://ftpmaster.internal/ubuntu resolute-proposed/main amd64 c-n-f Metadata [5004 B]
 35s Get:12 http://ftpmaster.internal/ubuntu resolute-proposed/restricted i386 Packages [3744 B]
 35s Get:13 http://ftpmaster.internal/ubuntu resolute-proposed/restricted amd64 Packages [64.6 kB]
 35s Get:14 http://ftpmaster.internal/ubuntu resolute-proposed/restricted amd64 c-n-f Metadata [336 B]
 35s Get:15 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 Packages [1995 kB]
 35s Get:16 http://ftpmaster.internal/ubuntu resolute-proposed/universe i386 Packages [836 kB]
 36s Get:17 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 c-n-f Metadata [52.7 kB]
 36s Get:18 http://ftpmaster.internal/ubuntu resolute-proposed/multiverse i386 Packages [14.7 kB]
 36s Get:19 http://ftpmaster.internal/ubuntu resolute-proposed/multiverse amd64 Packages [38.8 kB]
 36s Get:20 http://ftpmaster.internal/ubuntu resolute-proposed/multiverse amd64 c-n-f Metadata [1916 B]
 36s Fetched 6478 kB in 2s (3330 kB/s)
 37s Reading package lists...
 37s Hit:1 http://ftpmaster.internal/ubuntu resolute-proposed InRelease
 37s Hit:2 http://ftpmaster.internal/ubuntu resolute InRelease
 37s Hit:3 http://ftpmaster.internal/ubuntu resolute-updates InRelease
 37s Hit:4 http://ftpmaster.internal/ubuntu resolute-security InRelease
 38s Reading package lists...
 38s Reading package lists...
 38s Building dependency tree...
 38s Reading state information...
 38s Calculating upgrade...
 38s The following packages will be upgraded:
 38s   libfribidi0
 38s 1 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
 38s Need to get 26.5 kB of archives.
 38s After this operation, 0 B of additional disk space will be used.
 38s Get:1 http://ftpmaster.internal/ubuntu resolute/main amd64 libfribidi0 amd64 1.0.16-3 [26.5 kB]
 38s dpkg-preconfigure: unable to re-open stdin: No such file or directory
 38s Fetched 26.5 kB in 0s (1252 kB/s)
 39s (Reading database ... 
(Reading database ... 5%
(Reading database ... 10%
(Reading database ... 15%
(Reading database ... 20%
(Reading database ... 25%
(Reading database ... 30%
(Reading database ... 35%
(Reading database ... 40%
(Reading database ... 45%
(Reading database ... 50%
(Reading database ... 55%
(Reading database ... 60%
(Reading database ... 65%
(Reading database ... 70%
(Reading database ... 75%
(Reading database ... 80%
(Reading database ... 85%
(Reading database ... 90%
(Reading database ... 95%
(Reading database ... 100%
(Reading database ... 78534 files and directories currently installed.)
 39s Preparing to unpack .../libfribidi0_1.0.16-3_amd64.deb ...
 39s Unpacking libfribidi0:amd64 (1.0.16-3) over (1.0.16-1) ...
 39s Setting up libfribidi0:amd64 (1.0.16-3) ...
 39s Processing triggers for libc-bin (2.42-0ubuntu3) ...
 39s autopkgtest [23:56:12]: upgrading testbed (apt dist-upgrade and autopurge)
 39s Reading package lists...
 39s Building dependency tree...
 39s Reading state information...
 39s Calculating upgrade...
 39s 0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
 40s Reading package lists...
 40s Building dependency tree...
 40s Reading state information...
 40s Solving dependencies...
 40s 0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
 43s autopkgtest [23:56:16]: testbed running kernel: Linux 6.17.0-5-generic #5-Ubuntu SMP PREEMPT_DYNAMIC Mon Sep 22 10:00:33 UTC 2025
 44s autopkgtest [23:56:17]: @@@@@@@@@@@@@@@@@@@@ apt-source ggml
 48s Get:1 http://ftpmaster.internal/ubuntu resolute-proposed/universe ggml 0.9.4-3 (dsc) [3370 B]
 48s Get:2 http://ftpmaster.internal/ubuntu resolute-proposed/universe ggml 0.9.4-3 (tar) [2194 kB]
 48s Get:3 http://ftpmaster.internal/ubuntu resolute-proposed/universe ggml 0.9.4-3 (diff) [11.8 kB]
 48s gpgv: Signature made Sun Oct 19 21:12:36 2025 UTC
 48s gpgv:                using RSA key 419F7E9A47C3AB9519F1B0A339953A37DE4EB36B
 48s gpgv: Can't check signature: No public key
 48s dpkg-source: warning: cannot verify inline signature for ./ggml_0.9.4-3.dsc: no acceptable signature found
 49s autopkgtest [23:56:22]: testing package ggml version 0.9.4-3
 50s autopkgtest [23:56:23]: build not needed
 54s autopkgtest [23:56:27]: test libggml0-backend-cpu: preparing testbed
 54s Reading package lists...
 54s Building dependency tree...
 54s Reading state information...
 54s Solving dependencies...
 54s The following NEW packages will be installed:
 54s   libggml0 libggml0-backend-cpu libgomp1
 54s 0 upgraded, 3 newly installed, 0 to remove and 0 not upgraded.
 54s Need to get 1235 kB of archives.
 54s After this operation, 5938 kB of additional disk space will be used.
 54s Get:1 http://ftpmaster.internal/ubuntu resolute/main amd64 libgomp1 amd64 15.2.0-5ubuntu1 [151 kB]
 54s Get:2 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 libggml0-backend-cpu amd64 0.9.4-3 [711 kB]
 54s Get:3 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 libggml0 amd64 0.9.4-3 [373 kB]
 54s Fetched 1235 kB in 0s (4578 kB/s)
 54s Selecting previously unselected package libgomp1:amd64.
 54s (Reading database ... 
(Reading database ... 5%
(Reading database ... 10%
(Reading database ... 15%
(Reading database ... 20%
(Reading database ... 25%
(Reading database ... 30%
(Reading database ... 35%
(Reading database ... 40%
(Reading database ... 45%
(Reading database ... 50%
(Reading database ... 55%
(Reading database ... 60%
(Reading database ... 65%
(Reading database ... 70%
(Reading database ... 75%
(Reading database ... 80%
(Reading database ... 85%
(Reading database ... 90%
(Reading database ... 95%
(Reading database ... 100%
(Reading database ... 78534 files and directories currently installed.)
 54s Preparing to unpack .../libgomp1_15.2.0-5ubuntu1_amd64.deb ...
 54s Unpacking libgomp1:amd64 (15.2.0-5ubuntu1) ...
 54s Selecting previously unselected package libggml0-backend-cpu:amd64.
 54s Preparing to unpack .../libggml0-backend-cpu_0.9.4-3_amd64.deb ...
 54s Unpacking libggml0-backend-cpu:amd64 (0.9.4-3) ...
 54s Selecting previously unselected package libggml0:amd64.
 54s Preparing to unpack .../libggml0_0.9.4-3_amd64.deb ...
 54s Unpacking libggml0:amd64 (0.9.4-3) ...
 54s Setting up libgomp1:amd64 (15.2.0-5ubuntu1) ...
 54s Setting up libggml0-backend-cpu:amd64 (0.9.4-3) ...
 54s Setting up libggml0:amd64 (0.9.4-3) ...
 54s Processing triggers for libc-bin (2.42-0ubuntu3) ...
 55s autopkgtest [23:56:28]: test libggml0-backend-cpu: /usr/libexec/ggml/runtests
 55s autopkgtest [23:56:28]: test libggml0-backend-cpu: [-----------------------
 55s dpkg-architecture: warning: cannot determine CC system type, falling back to default (native compilation)
 55s load_backend: loaded CPU backend from /usr/lib/x86_64-linux-gnu/ggml/backends0/libggml-cpu-haswell.so
 55s Testing 1 devices
 55s 
 55s Backend 1/1: CPU
 55s   Skipping CPU backend
 55s 1/1 backends passed
 55s OK
 56s autopkgtest [23:56:29]: test libggml0-backend-cpu: -----------------------]
 56s libggml0-backend-cpu PASS
 56s autopkgtest [23:56:29]: test libggml0-backend-cpu:  - - - - - - - - - - results - - - - - - - - - -
 56s autopkgtest [23:56:29]: test libggml0-backend-blas: preparing testbed
 73s Creating nova instance adt-resolute-amd64-ggml-20251031-235533-juju-7f2275-prod-proposed-migration-environment-20-a2e36e32-01db-4661-a4d2-47c12274a09b from image adt/ubuntu-resolute-amd64-server-20251031.img (UUID eaf9d537-af66-471e-af1e-6f7da9a9a444)...
101s autopkgtest [23:57:14]: testbed dpkg architecture: amd64
101s autopkgtest [23:57:14]: testbed apt version: 3.1.11
102s autopkgtest [23:57:15]: @@@@@@@@@@@@@@@@@@@@ test bed setup
102s autopkgtest [23:57:15]: testbed release detected to be: resolute
102s autopkgtest [23:57:15]: updating testbed package index (apt update)
103s Get:1 http://ftpmaster.internal/ubuntu resolute-proposed InRelease [87.8 kB]
103s Hit:2 http://ftpmaster.internal/ubuntu resolute InRelease
103s Hit:3 http://ftpmaster.internal/ubuntu resolute-updates InRelease
103s Hit:4 http://ftpmaster.internal/ubuntu resolute-security InRelease
103s Get:5 http://ftpmaster.internal/ubuntu resolute-proposed/multiverse Sources [50.7 kB]
103s Get:6 http://ftpmaster.internal/ubuntu resolute-proposed/universe Sources [2759 kB]
103s Get:7 http://ftpmaster.internal/ubuntu resolute-proposed/restricted Sources [9848 B]
103s Get:8 http://ftpmaster.internal/ubuntu resolute-proposed/main Sources [155 kB]
103s Get:9 http://ftpmaster.internal/ubuntu resolute-proposed/main i386 Packages [160 kB]
103s Get:10 http://ftpmaster.internal/ubuntu resolute-proposed/main amd64 Packages [244 kB]
103s Get:11 http://ftpmaster.internal/ubuntu resolute-proposed/main amd64 c-n-f Metadata [5004 B]
103s Get:12 http://ftpmaster.internal/ubuntu resolute-proposed/restricted i386 Packages [3744 B]
103s Get:13 http://ftpmaster.internal/ubuntu resolute-proposed/restricted amd64 Packages [64.6 kB]
103s Get:14 http://ftpmaster.internal/ubuntu resolute-proposed/restricted amd64 c-n-f Metadata [336 B]
103s Get:15 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 Packages [1995 kB]
104s Get:16 http://ftpmaster.internal/ubuntu resolute-proposed/universe i386 Packages [836 kB]
104s Get:17 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 c-n-f Metadata [52.7 kB]
104s Get:18 http://ftpmaster.internal/ubuntu resolute-proposed/multiverse amd64 Packages [38.8 kB]
104s Get:19 http://ftpmaster.internal/ubuntu resolute-proposed/multiverse i386 Packages [14.7 kB]
104s Get:20 http://ftpmaster.internal/ubuntu resolute-proposed/multiverse amd64 c-n-f Metadata [1916 B]
104s Fetched 6478 kB in 1s (4988 kB/s)
105s Reading package lists...
105s Hit:1 http://ftpmaster.internal/ubuntu resolute-proposed InRelease
106s Hit:2 http://ftpmaster.internal/ubuntu resolute InRelease
106s Hit:3 http://ftpmaster.internal/ubuntu resolute-updates InRelease
106s Hit:4 http://ftpmaster.internal/ubuntu resolute-security InRelease
106s Reading package lists...
106s Reading package lists...
106s Building dependency tree...
106s Reading state information...
106s Calculating upgrade...
106s The following packages will be upgraded:
106s   libfribidi0
106s 1 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
106s Need to get 26.5 kB of archives.
106s After this operation, 0 B of additional disk space will be used.
106s Get:1 http://ftpmaster.internal/ubuntu resolute/main amd64 libfribidi0 amd64 1.0.16-3 [26.5 kB]
107s dpkg-preconfigure: unable to re-open stdin: No such file or directory
107s Fetched 26.5 kB in 0s (0 B/s)
107s (Reading database ... 
(Reading database ... 5%
(Reading database ... 10%
(Reading database ... 15%
(Reading database ... 20%
(Reading database ... 25%
(Reading database ... 30%
(Reading database ... 35%
(Reading database ... 40%
(Reading database ... 45%
(Reading database ... 50%
(Reading database ... 55%
(Reading database ... 60%
(Reading database ... 65%
(Reading database ... 70%
(Reading database ... 75%
(Reading database ... 80%
(Reading database ... 85%
(Reading database ... 90%
(Reading database ... 95%
(Reading database ... 100%
(Reading database ... 78534 files and directories currently installed.)
107s Preparing to unpack .../libfribidi0_1.0.16-3_amd64.deb ...
107s Unpacking libfribidi0:amd64 (1.0.16-3) over (1.0.16-1) ...
107s Setting up libfribidi0:amd64 (1.0.16-3) ...
107s Processing triggers for libc-bin (2.42-0ubuntu3) ...
107s autopkgtest [23:57:20]: upgrading testbed (apt dist-upgrade and autopurge)
107s Reading package lists...
107s Building dependency tree...
107s Reading state information...
107s Calculating upgrade...
107s 0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
108s Reading package lists...
108s Building dependency tree...
108s Reading state information...
108s Solving dependencies...
108s 0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
110s Reading package lists...
110s Building dependency tree...
110s Reading state information...
110s Solving dependencies...
110s The following NEW packages will be installed:
110s   libgfortran5 libggml0 libggml0-backend-blas libggml0-backend-cpu libgomp1
110s   libopenblas0-pthread
110s 0 upgraded, 6 newly installed, 0 to remove and 0 not upgraded.
110s Need to get 7573 kB of archives.
110s After this operation, 56.1 MB of additional disk space will be used.
110s Get:1 http://ftpmaster.internal/ubuntu resolute/main amd64 libgfortran5 amd64 15.2.0-5ubuntu1 [939 kB]
111s Get:2 http://ftpmaster.internal/ubuntu resolute/main amd64 libgomp1 amd64 15.2.0-5ubuntu1 [151 kB]
111s Get:3 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 libggml0-backend-cpu amd64 0.9.4-3 [711 kB]
111s Get:4 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 libggml0 amd64 0.9.4-3 [373 kB]
111s Get:5 http://ftpmaster.internal/ubuntu resolute/universe amd64 libopenblas0-pthread amd64 0.3.30+ds-3 [5382 kB]
111s Get:6 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 libggml0-backend-blas amd64 0.9.4-3 [16.8 kB]
112s Fetched 7573 kB in 1s (6892 kB/s)
112s Selecting previously unselected package libgfortran5:amd64.
112s (Reading database ... 
(Reading database ... 5%
(Reading database ... 10%
(Reading database ... 15%
(Reading database ... 20%
(Reading database ... 25%
(Reading database ... 30%
(Reading database ... 35%
(Reading database ... 40%
(Reading database ... 45%
(Reading database ... 50%
(Reading database ... 55%
(Reading database ... 60%
(Reading database ... 65%
(Reading database ... 70%
(Reading database ... 75%
(Reading database ... 80%
(Reading database ... 85%
(Reading database ... 90%
(Reading database ... 95%
(Reading database ... 100%
(Reading database ... 78534 files and directories currently installed.)
112s Preparing to unpack .../0-libgfortran5_15.2.0-5ubuntu1_amd64.deb ...
112s Unpacking libgfortran5:amd64 (15.2.0-5ubuntu1) ...
112s Selecting previously unselected package libgomp1:amd64.
112s Preparing to unpack .../1-libgomp1_15.2.0-5ubuntu1_amd64.deb ...
112s Unpacking libgomp1:amd64 (15.2.0-5ubuntu1) ...
112s Selecting previously unselected package libggml0-backend-cpu:amd64.
112s Preparing to unpack .../2-libggml0-backend-cpu_0.9.4-3_amd64.deb ...
112s Unpacking libggml0-backend-cpu:amd64 (0.9.4-3) ...
112s Selecting previously unselected package libggml0:amd64.
112s Preparing to unpack .../3-libggml0_0.9.4-3_amd64.deb ...
112s Unpacking libggml0:amd64 (0.9.4-3) ...
112s Selecting previously unselected package libopenblas0-pthread:amd64.
112s Preparing to unpack .../4-libopenblas0-pthread_0.3.30+ds-3_amd64.deb ...
112s Unpacking libopenblas0-pthread:amd64 (0.3.30+ds-3) ...
112s Selecting previously unselected package libggml0-backend-blas:amd64.
112s Preparing to unpack .../5-libggml0-backend-blas_0.9.4-3_amd64.deb ...
112s Unpacking libggml0-backend-blas:amd64 (0.9.4-3) ...
112s Setting up libgomp1:amd64 (15.2.0-5ubuntu1) ...
112s Setting up libgfortran5:amd64 (15.2.0-5ubuntu1) ...
112s Setting up libopenblas0-pthread:amd64 (0.3.30+ds-3) ...
112s update-alternatives: using /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3 to provide /usr/lib/x86_64-linux-gnu/libblas.so.3 (libblas.so.3-x86_64-linux-gnu) in auto mode
112s update-alternatives: using /usr/lib/x86_64-linux-gnu/openblas-pthread/liblapack.so.3 to provide /usr/lib/x86_64-linux-gnu/liblapack.so.3 (liblapack.so.3-x86_64-linux-gnu) in auto mode
112s update-alternatives: using /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblas.so.0 to provide /usr/lib/x86_64-linux-gnu/libopenblas.so.0 (libopenblas.so.0-x86_64-linux-gnu) in auto mode
112s Setting up libggml0-backend-cpu:amd64 (0.9.4-3) ...
112s Setting up libggml0:amd64 (0.9.4-3) ...
112s Setting up libggml0-backend-blas:amd64 (0.9.4-3) ...
112s Processing triggers for libc-bin (2.42-0ubuntu3) ...
116s autopkgtest [23:57:29]: test libggml0-backend-blas: /usr/libexec/ggml/runtests
116s autopkgtest [23:57:29]: test libggml0-backend-blas: [-----------------------
116s dpkg-architecture: warning: cannot determine CC system type, falling back to default (native compilation)
116s load_backend: loaded BLAS backend from /usr/lib/x86_64-linux-gnu/ggml/backends0/libggml-blas.so
116s load_backend: loaded CPU backend from /usr/lib/x86_64-linux-gnu/ggml/backends0/libggml-cpu-haswell.so
116s Testing 2 devices
116s 
116s Backend 1/2: BLAS
116s   Device description: BLAS
116s   Device memory: 0 MB (0 MB free)
116s 
116s   ABS(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   ABS(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   SGN(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   SGN(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   NEG(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   NEG(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   STEP(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   STEP(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   TANH(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   TANH(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   ELU(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   ELU(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   RELU(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   RELU(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   SIGMOID(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   SIGMOID(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   GELU(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   GELU(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   GELU_QUICK(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   GELU_QUICK(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   SILU(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   SILU(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   HARDSWISH(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   HARDSWISH(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   HARDSIGMOID(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   HARDSIGMOID(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   EXP(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   EXP(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   GELU_ERF(type=f16,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   GELU_ERF(type=f16,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   ABS(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   ABS(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   SGN(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   SGN(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   NEG(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   NEG(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   STEP(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   STEP(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   TANH(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   TANH(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   ELU(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   ELU(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   RELU(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   RELU(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   SIGMOID(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   SIGMOID(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   GELU(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   GELU(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   GELU_QUICK(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   GELU_QUICK(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   SILU(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   SILU(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   HARDSWISH(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   HARDSWISH(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   HARDSIGMOID(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   HARDSIGMOID(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   EXP(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   EXP(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   GELU_ERF(type=f16,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   GELU_ERF(type=f16,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   ABS(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   ABS(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   SGN(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   SGN(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   NEG(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   NEG(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   STEP(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   STEP(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   TANH(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   TANH(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   ELU(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   ELU(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   RELU(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   RELU(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   SIGMOID(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   SIGMOID(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   GELU(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   GELU(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   GELU_QUICK(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   GELU_QUICK(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   SILU(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   SILU(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   HARDSWISH(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   HARDSWISH(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   HARDSIGMOID(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   HARDSIGMOID(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   EXP(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   EXP(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   GELU_ERF(type=f32,ne_a=[128,2,2,2],v=0): not supported [BLAS] 
116s   GELU_ERF(type=f32,ne_a=[5,7,11,13],v=0): not supported [BLAS] 
116s   ABS(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   ABS(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   SGN(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   SGN(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   NEG(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   NEG(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   STEP(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   STEP(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   TANH(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   TANH(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   ELU(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   ELU(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   RELU(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   RELU(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   SIGMOID(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   SIGMOID(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   GELU(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   GELU(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   GELU_QUICK(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   GELU_QUICK(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   SILU(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   SILU(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   HARDSWISH(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   HARDSWISH(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   HARDSIGMOID(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   HARDSIGMOID(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   EXP(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   EXP(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   GELU_ERF(type=f32,ne_a=[128,2,2,2],v=1): not supported [BLAS] 
116s   GELU_ERF(type=f32,ne_a=[5,7,11,13],v=1): not supported [BLAS] 
116s   REGLU(type=f16,ne_a=[128,2,2,2],v=0,swapped=0): not supported [BLAS] 
116s   REGLU(type=f16,ne_a=[5,7,11,13],v=0,swapped=0): not supported [BLAS] 
116s   REGLU(type=f16,ne_a=[128,2,2,2],v=0,swapped=1): not supported [BLAS] 
116s   REGLU(type=f16,ne_a=[5,7,11,13],v=0,swapped=1): not supported [BLAS] 
116s   REGLU(type=f16,ne_a=[128,2,2,2],v=0,split): not supported [BLAS] 
116s   REGLU(type=f16,ne_a=[5,7,11,13],v=0,split): not supported [BLAS] 
116s   GEGLU(type=f16,ne_a=[128,2,2,2],v=0,swapped=0): not supported [BLAS] 
116s   GEGLU(type=f16,ne_a=[5,7,11,13],v=0,swapped=0): not supported [BLAS] 
116s   GEGLU(type=f16,ne_a=[128,2,2,2],v=0,swapped=1): not supported [BLAS] 
116s   GEGLU(type=f16,ne_a=[5,7,11,13],v=0,swapped=1): not supported [BLAS] 
116s   GEGLU(type=f16,ne_a=[128,2,2,2],v=0,split): not supported [BLAS] 
116s   GEGLU(type=f16,ne_a=[5,7,11,13],v=0,split): not supported [BLAS] 
116s   SWIGLU(type=f16,ne_a=[128,2,2,2],v=0,swapped=0): not supported [BLAS] 
116s   SWIGLU(type=f16,ne_a=[5,7,11,13],v=0,swapped=0): not supported [BLAS] 
116s   SWIGLU(type=f16,ne_a=[128,2,2,2],v=0,swapped=1): not supported [BLAS] 
116s   SWIGLU(type=f16,ne_a=[5,7,11,13],v=0,swapped=1): not supported [BLAS] 
116s   SWIGLU(type=f16,ne_a=[128,2,2,2],v=0,split): not supported [BLAS] 
116s   SWIGLU(type=f16,ne_a=[5,7,11,13],v=0,split): not supported [BLAS] 
116s   GEGLU_ERF(type=f16,ne_a=[128,2,2,2],v=0,swapped=0): not supported [BLAS] 
116s   GEGLU_ERF(type=f16,ne_a=[5,7,11,13],v=0,swapped=0): not supported [BLAS] 
116s   GEGLU_ERF(type=f16,ne_a=[128,2,2,2],v=0,swapped=1): not supported [BLAS] 
116s   GEGLU_ERF(type=f16,ne_a=[5,7,11,13],v=0,swapped=1): not supported [BLAS] 
116s   GEGLU_ERF(type=f16,ne_a=[128,2,2,2],v=0,split): not supported [BLAS] 
116s   GEGLU_ERF(type=f16,ne_a=[5,7,11,13],v=0,split): not supported [BLAS] 
116s   GEGLU_QUICK(type=f16,ne_a=[128,2,2,2],v=0,swapped=0): not supported [BLAS] 
116s   GEGLU_QUICK(type=f16,ne_a=[5,7,11,13],v=0,swapped=0): not supported [BLAS] 
116s   GEGLU_QUICK(type=f16,ne_a=[128,2,2,2],v=0,swapped=1): not supported [BLAS] 
116s   GEGLU_QUICK(type=f16,ne_a=[5,7,11,13],v=0,swapped=1): not supported [BLAS] 
116s   GEGLU_QUICK(type=f16,ne_a=[128,2,2,2],v=0,split): not supported [BLAS] 
116s   GEGLU_QUICK(type=f16,ne_a=[5,7,11,13],v=0,split): not supported [BLAS] 
116s   REGLU(type=f16,ne_a=[128,2,2,2],v=1,swapped=0): not supported [BLAS] 
116s   REGLU(type=f16,ne_a=[5,7,11,13],v=1,swapped=0): not supported [BLAS] 
116s   REGLU(type=f16,ne_a=[128,2,2,2],v=1,swapped=1): not supported [BLAS] 
116s   REGLU(type=f16,ne_a=[5,7,11,13],v=1,swapped=1): not supported [BLAS] 
116s   REGLU(type=f16,ne_a=[128,2,2,2],v=1,split): not supported [BLAS] 
116s   REGLU(type=f16,ne_a=[5,7,11,13],v=1,split): not supported [BLAS] 
116s   GEGLU(type=f16,ne_a=[128,2,2,2],v=1,swapped=0): not supported [BLAS] 
116s   GEGLU(type=f16,ne_a=[5,7,11,13],v=1,swapped=0): not supported [BLAS] 
116s   GEGLU(type=f16,ne_a=[128,2,2,2],v=1,swapped=1): not supported [BLAS] 
116s   GEGLU(type=f16,ne_a=[5,7,11,13],v=1,swapped=1): not supported [BLAS] 
116s   GEGLU(type=f16,ne_a=[128,2,2,2],v=1,split): not supported [BLAS] 
116s   GEGLU(type=f16,ne_a=[5,7,11,13],v=1,split): not supported [BLAS] 
116s   SWIGLU(type=f16,ne_a=[128,2,2,2],v=1,swapped=0): not supported [BLAS] 
116s   SWIGLU(type=f16,ne_a=[5,7,11,13],v=1,swapped=0): not supported [BLAS] 
116s   SWIGLU(type=f16,ne_a=[128,2,2,2],v=1,swapped=1): not supported [BLAS] 
116s   SWIGLU(type=f16,ne_a=[5,7,11,13],v=1,swapped=1): not supported [BLAS] 
116s   SWIGLU(type=f16,ne_a=[128,2,2,2],v=1,split): not supported [BLAS] 
116s   SWIGLU(type=f16,ne_a=[5,7,11,13],v=1,split): not supported [BLAS] 
116s   GEGLU_ERF(type=f16,ne_a=[128,2,2,2],v=1,swapped=0): not supported [BLAS] 
116s   GEGLU_ERF(type=f16,ne_a=[5,7,11,13],v=1,swapped=0): not supported [BLAS] 
116s   GEGLU_ERF(type=f16,ne_a=[128,2,2,2],v=1,swapped=1): not supported [BLAS] 
116s   GEGLU_ERF(type=f16,ne_a=[5,7,11,13],v=1,swapped=1): not supported [BLAS] 
116s   GEGLU_ERF(type=f16,ne_a=[128,2,2,2],v=1,split): not supported [BLAS] 
116s   GEGLU_ERF(type=f16,ne_a=[5,7,11,13],v=1,split): not supported [BLAS] 
116s   GEGLU_QUICK(type=f16,ne_a=[128,2,2,2],v=1,swapped=0): not supported [BLAS] 
116s   GEGLU_QUICK(type=f16,ne_a=[5,7,11,13],v=1,swapped=0): not supported [BLAS] 
116s   GEGLU_QUICK(type=f16,ne_a=[128,2,2,2],v=1,swapped=1): not supported [BLAS] 
116s   GEGLU_QUICK(type=f16,ne_a=[5,7,11,13],v=1,swapped=1): not supported [BLAS] 
116s   GEGLU_QUICK(type=f16,ne_a=[128,2,2,2],v=1,split): not supported [BLAS] 
116s   GEGLU_QUICK(type=f16,ne_a=[5,7,11,13],v=1,split): not supported [BLAS] 
116s   REGLU(type=f32,ne_a=[128,2,2,2],v=0,swapped=0): not supported [BLAS] 
116s   REGLU(type=f32,ne_a=[5,7,11,13],v=0,swapped=0): not supported [BLAS] 
116s   REGLU(type=f32,ne_a=[128,2,2,2],v=0,swapped=1): not supported [BLAS] 
116s   REGLU(type=f32,ne_a=[5,7,11,13],v=0,swapped=1): not supported [BLAS] 
116s   REGLU(type=f32,ne_a=[128,2,2,2],v=0,split): not supported [BLAS] 
116s   REGLU(type=f32,ne_a=[5,7,11,13],v=0,split): not supported [BLAS] 
116s   GEGLU(type=f32,ne_a=[128,2,2,2],v=0,swapped=0): not supported [BLAS] 
116s   GEGLU(type=f32,ne_a=[5,7,11,13],v=0,swapped=0): not supported [BLAS] 
116s   GEGLU(type=f32,ne_a=[128,2,2,2],v=0,swapped=1): not supported [BLAS] 
116s   GEGLU(type=f32,ne_a=[5,7,11,13],v=0,swapped=1): not supported [BLAS] 
116s   GEGLU(type=f32,ne_a=[128,2,2,2],v=0,split): not supported [BLAS] 
116s   GEGLU(type=f32,ne_a=[5,7,11,13],v=0,split): not supported [BLAS] 
116s   SWIGLU(type=f32,ne_a=[128,2,2,2],v=0,swapped=0): not supported [BLAS] 
116s   SWIGLU(type=f32,ne_a=[5,7,11,13],v=0,swapped=0): not supported [BLAS] 
116s   SWIGLU(type=f32,ne_a=[128,2,2,2],v=0,swapped=1): not supported [BLAS] 
116s   SWIGLU(type=f32,ne_a=[5,7,11,13],v=0,swapped=1): not supported [BLAS] 
116s   SWIGLU(type=f32,ne_a=[128,2,2,2],v=0,split): not supported [BLAS] 
116s   SWIGLU(type=f32,ne_a=[5,7,11,13],v=0,split): not supported [BLAS] 
116s   GEGLU_ERF(type=f32,ne_a=[128,2,2,2],v=0,swapped=0): not supported [BLAS] 
116s   GEGLU_ERF(type=f32,ne_a=[5,7,11,13],v=0,swapped=0): not supported [BLAS] 
116s   GEGLU_ERF(type=f32,ne_a=[128,2,2,2],v=0,swapped=1): not supported [BLAS] 
116s   GEGLU_ERF(type=f32,ne_a=[5,7,11,13],v=0,swapped=1): not supported [BLAS] 
116s   GEGLU_ERF(type=f32,ne_a=[128,2,2,2],v=0,split): not supported [BLAS] 
116s   GEGLU_ERF(type=f32,ne_a=[5,7,11,13],v=0,split): not supported [BLAS] 
116s   GEGLU_QUICK(type=f32,ne_a=[128,2,2,2],v=0,swapped=0): not supported [BLAS] 
116s   GEGLU_QUICK(type=f32,ne_a=[5,7,11,13],v=0,swapped=0): not supported [BLAS] 
116s   GEGLU_QUICK(type=f32,ne_a=[128,2,2,2],v=0,swapped=1): not supported [BLAS] 
116s   GEGLU_QUICK(type=f32,ne_a=[5,7,11,13],v=0,swapped=1): not supported [BLAS] 
116s   GEGLU_QUICK(type=f32,ne_a=[128,2,2,2],v=0,split): not supported [BLAS] 
116s   GEGLU_QUICK(type=f32,ne_a=[5,7,11,13],v=0,split): not supported [BLAS] 
116s   REGLU(type=f32,ne_a=[128,2,2,2],v=1,swapped=0): not supported [BLAS] 
116s   REGLU(type=f32,ne_a=[5,7,11,13],v=1,swapped=0): not supported [BLAS] 
116s   REGLU(type=f32,ne_a=[128,2,2,2],v=1,swapped=1): not supported [BLAS] 
116s   REGLU(type=f32,ne_a=[5,7,11,13],v=1,swapped=1): not supported [BLAS] 
116s   REGLU(type=f32,ne_a=[128,2,2,2],v=1,split): not supported [BLAS] 
116s   REGLU(type=f32,ne_a=[5,7,11,13],v=1,split): not supported [BLAS] 
116s   GEGLU(type=f32,ne_a=[128,2,2,2],v=1,swapped=0): not supported [BLAS] 
116s   GEGLU(type=f32,ne_a=[5,7,11,13],v=1,swapped=0): not supported [BLAS] 
116s   GEGLU(type=f32,ne_a=[128,2,2,2],v=1,swapped=1): not supported [BLAS] 
116s   GEGLU(type=f32,ne_a=[5,7,11,13],v=1,swapped=1): not supported [BLAS] 
116s   GEGLU(type=f32,ne_a=[128,2,2,2],v=1,split): not supported [BLAS] 
116s   GEGLU(type=f32,ne_a=[5,7,11,13],v=1,split): not supported [BLAS] 
116s   SWIGLU(type=f32,ne_a=[128,2,2,2],v=1,swapped=0): not supported [BLAS] 
116s   SWIGLU(type=f32,ne_a=[5,7,11,13],v=1,swapped=0): not supported [BLAS] 
116s   SWIGLU(type=f32,ne_a=[128,2,2,2],v=1,swapped=1): not supported [BLAS] 
116s   SWIGLU(type=f32,ne_a=[5,7,11,13],v=1,swapped=1): not supported [BLAS] 
116s   SWIGLU(type=f32,ne_a=[128,2,2,2],v=1,split): not supported [BLAS] 
116s   SWIGLU(type=f32,ne_a=[5,7,11,13],v=1,split): not supported [BLAS] 
116s   GEGLU_ERF(type=f32,ne_a=[128,2,2,2],v=1,swapped=0): not supported [BLAS] 
116s   GEGLU_ERF(type=f32,ne_a=[5,7,11,13],v=1,swapped=0): not supported [BLAS] 
116s   GEGLU_ERF(type=f32,ne_a=[128,2,2,2],v=1,swapped=1): not supported [BLAS] 
116s   GEGLU_ERF(type=f32,ne_a=[5,7,11,13],v=1,swapped=1): not supported [BLAS] 
116s   GEGLU_ERF(type=f32,ne_a=[128,2,2,2],v=1,split): not supported [BLAS] 
116s   GEGLU_ERF(type=f32,ne_a=[5,7,11,13],v=1,split): not supported [BLAS] 
116s   GEGLU_QUICK(type=f32,ne_a=[128,2,2,2],v=1,swapped=0): not supported [BLAS] 
116s   GEGLU_QUICK(type=f32,ne_a=[5,7,11,13],v=1,swapped=0): not supported [BLAS] 
116s   GEGLU_QUICK(type=f32,ne_a=[128,2,2,2],v=1,swapped=1): not supported [BLAS] 
116s   GEGLU_QUICK(type=f32,ne_a=[5,7,11,13],v=1,swapped=1): not supported [BLAS] 
116s   GEGLU_QUICK(type=f32,ne_a=[128,2,2,2],v=1,split): not supported [BLAS] 
116s   GEGLU_QUICK(type=f32,ne_a=[5,7,11,13],v=1,split): not supported [BLAS] 
116s   SWIGLU_OAI(type=f32,ne_a=[128,2,2,2],v=0,alpha=0.500000,limit=2.000000): not supported [BLAS] 
116s   SWIGLU_OAI(type=f32,ne_a=[128,2,2,2],v=0,alpha=0.500000,limit=7.000000): not supported [BLAS] 
116s   SWIGLU_OAI(type=f32,ne_a=[128,2,2,2],v=0,alpha=1.702000,limit=2.000000): not supported [BLAS] 
116s   SWIGLU_OAI(type=f32,ne_a=[128,2,2,2],v=0,alpha=1.702000,limit=7.000000): not supported [BLAS] 
116s   SWIGLU_OAI(type=f32,ne_a=[128,2,2,2],v=1,alpha=0.500000,limit=2.000000): not supported [BLAS] 
116s   SWIGLU_OAI(type=f32,ne_a=[128,2,2,2],v=1,alpha=0.500000,limit=7.000000): not supported [BLAS] 
116s   SWIGLU_OAI(type=f32,ne_a=[128,2,2,2],v=1,alpha=1.702000,limit=2.000000): not supported [BLAS] 
116s   SWIGLU_OAI(type=f32,ne_a=[128,2,2,2],v=1,alpha=1.702000,limit=7.000000): not supported [BLAS] 
116s   GET_ROWS(type=f32,n=76800,m=5,r=4,be1=1,be2=2,v=0): not supported [BLAS] 
116s   GET_ROWS(type=f32,n=256,m=80000,r=70000,be1=2,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=f32,n=256,m=5,r=4,be1=700,be2=100,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q4_0,n=76800,m=5,r=4,be1=1,be2=2,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q4_0,n=256,m=80000,r=70000,be1=2,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q4_0,n=256,m=5,r=4,be1=700,be2=100,v=0): not supported [BLAS] 
116s   GET_ROWS(type=f32,n=1,m=8,r=2,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=f32,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=f32,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=f32,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=f32,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=f16,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=f16,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=f16,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=f16,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=bf16,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=bf16,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=bf16,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=bf16,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q4_0,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q4_0,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q4_0,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q4_0,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q4_1,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q4_1,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q4_1,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q4_1,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q5_0,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q5_0,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q5_0,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q5_0,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q5_1,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q5_1,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q5_1,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q5_1,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q8_0,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q8_0,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q8_0,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q8_0,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=mxfp4,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=mxfp4,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=mxfp4,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=mxfp4,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q2_K,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q2_K,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q2_K,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q2_K,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q3_K,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q3_K,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q3_K,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q3_K,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q4_K,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q4_K,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q4_K,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q4_K,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q5_K,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q5_K,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q5_K,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q5_K,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q6_K,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q6_K,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=q6_K,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=q6_K,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq2_xxs,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq2_xxs,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq2_xxs,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq2_xxs,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq2_xs,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq2_xs,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq2_xs,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq2_xs,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq2_s,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq2_s,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq2_s,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq2_s,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq3_xxs,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq3_xxs,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq3_xxs,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq3_xxs,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq1_s,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq1_s,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq1_s,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq1_s,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq1_m,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq1_m,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq1_m,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq1_m,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq4_nl,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq4_nl,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq4_nl,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq4_nl,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq3_s,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq3_s,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq3_s,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq3_s,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq4_xs,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq4_xs,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=iq4_xs,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=iq4_xs,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=i32,n=256,m=5,r=4,be1=1,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=i32,n=256,m=5,r=4,be1=1,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS(type=i32,n=256,m=5,r=4,be1=7,be2=1,v=0): not supported [BLAS] 
116s   GET_ROWS(type=i32,n=256,m=5,r=4,be1=7,be2=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=f32,n=1,m=8,r=2,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=f32,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=f32,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=f16,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=f16,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=bf16,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=bf16,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q4_0,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q4_0,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q4_1,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q4_1,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q5_0,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q5_0,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q5_1,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q5_1,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q8_0,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q8_0,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=mxfp4,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=mxfp4,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q2_K,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q2_K,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q3_K,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q3_K,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q4_K,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q4_K,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q5_K,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q5_K,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q6_K,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=q6_K,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq2_xxs,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq2_xxs,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq2_xs,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq2_xs,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq2_s,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq2_s,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq3_xxs,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq3_xxs,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq1_s,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq1_s,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq1_m,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq1_m,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq4_nl,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq4_nl,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq3_s,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq3_s,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq4_xs,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=iq4_xs,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   GET_ROWS_BACK(type=i32,n=256,m=5,r=4,b=1,v=0): not supported [BLAS] 
116s   GET_ROWS_BACK(type=i32,n=256,m=5,r=4,b=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[1,8,1,3],nr23=[1,1],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i32,ne=[1,8,1,3],nr23=[1,1],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q8_0,type_idx=i32,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f32,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=f16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=bf16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q8_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q8_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q8_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q8_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q8_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q8_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q8_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q8_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q8_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q8_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q8_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q8_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=mxfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=mxfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=mxfp4,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=mxfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=mxfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=mxfp4,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=mxfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=mxfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=mxfp4,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=mxfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=mxfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=mxfp4,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q2_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q2_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q2_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q2_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q2_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q2_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q2_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q2_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q2_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q2_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q2_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q2_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q3_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q3_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q3_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q3_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q3_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q3_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q3_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q3_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q3_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q3_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q3_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q3_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q4_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q4_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q5_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q5_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q6_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q6_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q6_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q6_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q6_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q6_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q6_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q6_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q6_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=q6_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q6_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=q6_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq2_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq2_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq3_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq3_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq3_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq3_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq3_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq3_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq3_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq3_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq3_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq3_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq3_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq3_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq1_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq1_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq1_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq1_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq1_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq1_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq1_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq1_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq1_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq1_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq1_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq1_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq1_m,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq1_m,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq1_m,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq1_m,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq1_m,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq1_m,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq1_m,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq1_m,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq1_m,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq1_m,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq1_m,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq1_m,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq4_nl,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq4_nl,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq4_nl,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq4_nl,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq4_nl,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq4_nl,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq4_nl,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq4_nl,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq4_nl,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq4_nl,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq4_nl,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq4_nl,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq3_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq3_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq3_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq3_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq3_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq3_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq3_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq3_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq3_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq3_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq3_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq3_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq4_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq4_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq4_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq4_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq4_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq4_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq4_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq4_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq4_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0): not supported [BLAS] 
116s   SET_ROWS(type=iq4_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq4_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1): not supported [BLAS] 
116s   SET_ROWS(type=iq4_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=2,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=1,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=3,s0=2,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=1,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=1,s0=2,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=1,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=1,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=1,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=1,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=1,p0=1,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=2,p0=0,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=2,p0=0,p1=1): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=2,p0=1,p1=0): not supported [BLAS] 
116s   POOL_2D(pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=2,p0=1,p1=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[3000,128,1,1],ne_kernel=[3,128,1280,1],s0=1,s1=0,p0=1,p1=0,d0=1,d1=0,is_2D=0): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f16,dst_type=f32,ne_input=[3000,128,1,1],ne_kernel=[3,128,1280,1],s0=1,s1=0,p0=1,p1=0,d0=1,d1=0,is_2D=0): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[3000,128,1,1],ne_kernel=[3,128,1280,1],s0=1,s1=0,p0=1,p1=0,d0=1,d1=0,is_2D=0): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=1,s1=0,p0=0,p1=0,d0=1,d1=0,is_2D=0): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=1,s1=0,p0=0,p1=0,d0=3,d1=0,is_2D=0): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=1,s1=0,p0=3,p1=0,d0=1,d1=0,is_2D=0): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=1,s1=0,p0=3,p1=0,d0=3,d1=0,is_2D=0): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=3,s1=0,p0=0,p1=0,d0=1,d1=0,is_2D=0): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=3,s1=0,p0=0,p1=0,d0=3,d1=0,is_2D=0): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=3,s1=0,p0=3,p1=0,d0=1,d1=0,is_2D=0): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=3,s1=0,p0=3,p1=0,d0=3,d1=0,is_2D=0): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[10,10,3,1],ne_kernel=[3,3,3,1],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f16,dst_type=f32,ne_input=[10,10,3,1],ne_kernel=[3,3,3,1],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[10,10,3,1],ne_kernel=[3,3,3,1],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=0,p1=0,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=0,p1=0,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=0,p1=0,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=0,p1=0,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=0,p1=3,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=0,p1=3,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=0,p1=3,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=0,p1=3,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=3,p1=0,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=3,p1=0,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=3,p1=0,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=3,p1=0,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=3,p1=3,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=3,p1=3,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=3,p1=3,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=3,p1=3,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=0,p1=0,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=0,p1=0,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=0,p1=0,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=0,p1=0,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=0,p1=3,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=0,p1=3,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=0,p1=3,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=0,p1=3,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=3,p1=0,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=3,p1=0,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=3,p1=0,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=3,p1=0,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=3,p1=3,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=3,p1=3,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=3,p1=3,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=3,p0=3,p1=3,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=0,p1=0,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=0,p1=0,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=0,p1=0,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=0,p1=0,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=0,p1=3,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=0,p1=3,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=0,p1=3,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=0,p1=3,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=3,p1=0,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=3,p1=0,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=3,p1=0,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=3,p1=0,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=3,p1=3,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=3,p1=3,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=3,p1=3,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=1,p0=3,p1=3,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=0,p1=0,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=0,p1=0,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=0,p1=0,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=0,p1=0,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=0,p1=3,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=0,p1=3,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=0,p1=3,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=0,p1=3,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=3,p1=0,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=3,p1=0,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=3,p1=0,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=3,p1=0,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=3,p1=3,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=3,p1=3,d0=1,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=3,p1=3,d0=3,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=3,s1=3,p0=3,p1=3,d0=3,d1=3,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[12,12,1,32],ne_kernel=[3,3,1,32],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[12,12,2,32],ne_kernel=[3,3,2,32],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[12,12,1,1024],ne_kernel=[3,3,1,1024],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[12,12,2,1024],ne_kernel=[3,3,2,1024],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[12,12,1,2048],ne_kernel=[3,3,1,2048],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[12,12,2,2048],ne_kernel=[3,3,2,2048],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[12,12,1,2560],ne_kernel=[3,3,1,2560],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[12,12,2,2560],ne_kernel=[3,3,2,2560],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL(type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[5,5,1,32],ne_kernel=[3,4,1,32],s0=1,s1=1,p0=0,p1=0,d0=1,d1=1,is_2D=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[10,10,10,9],ne_kernel=[3,3,3,1],IC=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f16,dst_type=f32,ne_input=[10,10,10,9],ne_kernel=[3,3,3,1],IC=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[10,10,10,9],ne_kernel=[3,3,3,1],IC=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=1,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=1,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=1,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=0,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=0,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=0,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=1,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=1,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=1,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=1,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0): not supported [BLAS] 
116s   IM2COL_3D(type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D(ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0): not supported [BLAS] 
116s   CONV_2D_DW(ne_input=[17,34,9,1],ne_kernel=[3,3,1,9],stride=1,padding=0,dilation=1,cwhn=0): not supported [BLAS] 
116s   CONV_2D_DW(ne_input=[17,34,9,1],ne_kernel=[3,3,1,9],stride=1,padding=0,dilation=1,cwhn=1): not supported [BLAS] 
116s   CONV_2D_DW(ne_input=[32,8,64,1],ne_kernel=[3,3,1,64],stride=2,padding=1,dilation=1,cwhn=0): not supported [BLAS] 
116s   CONV_2D_DW(ne_input=[32,8,64,1],ne_kernel=[3,3,1,64],stride=2,padding=1,dilation=1,cwhn=1): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=4,ID=8,IH=8,IW=8,OC=8,KD=1,KH=1,KW=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16): not supported [BLAS] 
116s   CONV_3D(N=1,IC=4,ID=8,IH=8,IW=8,OC=8,KD=1,KH=1,KW=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1,1,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1,1,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1,1,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1,1,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1,1,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1,1,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1,1,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1,1,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1,1,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[3,1,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[3,1,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[3,1,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[3,1,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[3,1,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[3,1,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[3,1,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[3,1,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[3,1,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1337,1,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1337,1,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1337,1,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1337,1,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1337,1,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1337,1,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1337,1,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1337,1,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1337,1,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1,1,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1,1,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1,1,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1,1,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1,1,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1,1,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1,1,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1,1,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1,1,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[3,1,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[3,1,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[3,1,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[3,1,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[3,1,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[3,1,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[3,1,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[3,1,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[3,1,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1337,1,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1337,1,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1337,1,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1337,1,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1337,1,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1337,1,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1337,1,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1337,1,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1337,1,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1,9,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1,9,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1,9,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1,9,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1,9,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1,9,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1,9,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1,9,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1,9,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[3,9,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[3,9,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[3,9,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[3,9,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[3,9,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[3,9,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[3,9,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[3,9,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[3,9,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1337,9,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1337,9,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1337,9,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1337,9,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1337,9,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1337,9,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1337,9,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1337,9,1,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1337,9,1,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1,9,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1,9,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1,9,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1,9,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1,9,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1,9,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1,9,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1,9,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1,9,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[3,9,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[3,9,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[3,9,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[3,9,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[3,9,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[3,9,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[3,9,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[3,9,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[3,9,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1337,9,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1337,9,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1337,9,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1337,9,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1337,9,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1337,9,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1337,9,7,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1337,9,7,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1337,9,7,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[197,32,1,1],ne_kernel=[16,32,32,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[3,2,1,1],ne_kernel=[2,3,2,1],s0=3,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[3,2,1,1],ne_kernel=[2,3,2,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[3,2,1,1],ne_kernel=[2,3,2,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[3,2,1,1],ne_kernel=[3,2,2,1],s0=2,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[3,2,1,1],ne_kernel=[3,2,2,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[3,2,1,1],ne_kernel=[3,1,2,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[3,1,1,1],s0=1,p0=0,d0=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_2D(ne_input=[3,2,3,1],ne_kernel=[2,2,1,3],stride=1): not supported [BLAS] 
116s   CONV_TRANSPOSE_2D(ne_input=[10,10,9,1],ne_kernel=[3,3,1,9],stride=2): not supported [BLAS] 
116s   COUNT_EQUAL(type=f32,ne=[4,500,1,1]): not supported [BLAS] 
116s   COUNT_EQUAL(type=f32,ne=[4,5000,1,1]): not supported [BLAS] 
116s   ARGMAX(type=f32,ne=[32,1,1,1]): not supported [BLAS] 
116s   ARGMAX(type=f32,ne=[32,513,1,1]): not supported [BLAS] 
116s   ARGMAX(type=f32,ne=[100,10,1,1]): not supported [BLAS] 
116s   ARGMAX(type=f32,ne=[1024,10,1,1]): not supported [BLAS] 
116s   ARGMAX(type=f32,ne=[1024,12,1,1]): not supported [BLAS] 
116s   ARGMAX(type=f32,ne=[2000,10,1,1]): not supported [BLAS] 
116s   ARGMAX(type=f32,ne=[5438,3,1,1]): not supported [BLAS] 
116s   REPEAT(type=f32,ne=[10,5,4,1],nr=[1,1,1,1]): not supported [BLAS] 
116s   REPEAT(type=f32,ne=[10,5,4,1],nr=[2,1,1,1]): not supported [BLAS] 
116s   REPEAT(type=f32,ne=[10,5,4,1],nr=[1,2,1,1]): not supported [BLAS] 
116s   REPEAT(type=f32,ne=[10,5,4,1],nr=[1,1,2,1]): not supported [BLAS] 
116s   REPEAT(type=f32,ne=[10,5,4,1],nr=[1,1,1,2]): not supported [BLAS] 
116s   REPEAT(type=i32,ne=[10,5,4,1],nr=[2,1,1,1]): not supported [BLAS] 
116s   REPEAT(type=i16,ne=[10,5,4,1],nr=[1,1,1,2]): not supported [BLAS] 
116s   REPEAT(type=f32,ne=[10,5,4,3],nr=[1,1,1,1]): not supported [BLAS] 
116s   REPEAT(type=f32,ne=[10,5,4,3],nr=[2,1,1,1]): not supported [BLAS] 
116s   REPEAT(type=f32,ne=[10,5,4,3],nr=[1,2,1,1]): not supported [BLAS] 
116s   REPEAT(type=f32,ne=[10,5,4,3],nr=[1,1,2,1]): not supported [BLAS] 
116s   REPEAT(type=f32,ne=[10,5,4,3],nr=[1,1,1,2]): not supported [BLAS] 
116s   REPEAT(type=i32,ne=[10,5,4,3],nr=[2,1,1,1]): not supported [BLAS] 
116s   REPEAT(type=i16,ne=[10,5,4,3],nr=[1,1,1,2]): not supported [BLAS] 
116s   REPEAT_BACK(type=f32,ne=[8,6,4,2],nr=[1,1,1,1],v=0): not supported [BLAS] 
116s   REPEAT_BACK(type=f32,ne=[8,6,4,2],nr=[2,1,1,1],v=0): not supported [BLAS] 
116s   REPEAT_BACK(type=f32,ne=[8,6,4,2],nr=[1,2,1,1],v=0): not supported [BLAS] 
116s   REPEAT_BACK(type=f32,ne=[8,6,4,2],nr=[1,1,2,1],v=0): not supported [BLAS] 
116s   REPEAT_BACK(type=f32,ne=[8,6,4,2],nr=[1,1,1,2],v=0): not supported [BLAS] 
116s   REPEAT_BACK(type=f32,ne=[8,6,4,2],nr=[1,1,1,1],v=1): not supported [BLAS] 
116s   REPEAT_BACK(type=f32,ne=[8,6,4,2],nr=[2,1,1,1],v=1): not supported [BLAS] 
116s   REPEAT_BACK(type=f32,ne=[8,6,4,2],nr=[1,2,1,1],v=1): not supported [BLAS] 
116s   REPEAT_BACK(type=f32,ne=[8,6,4,2],nr=[1,1,2,1],v=1): not supported [BLAS] 
116s   REPEAT_BACK(type=f32,ne=[8,6,4,2],nr=[1,1,1,2],v=1): not supported [BLAS] 
116s   DUP(type=f32,ne=[10,10,20,1]): not supported [BLAS] 
116s   DUP(type=f16,ne=[10,10,20,1]): not supported [BLAS] 
116s   DUP(type=i32,ne=[10,10,20,1]): not supported [BLAS] 
116s   DUP(type=i16,ne=[10,10,20,1]): not supported [BLAS] 
116s   DUP(type=f32,ne=[10,10,5,1],permute=[0,2,1,3]): not supported [BLAS] 
116s   DUP(type=f16,ne=[10,10,5,1],permute=[0,2,1,3]): not supported [BLAS] 
116s   DUP(type=f32,ne=[10,10,5,1],permute=[1,0,2,3]): not supported [BLAS] 
116s   DUP(type=f16,ne=[10,10,5,1],permute=[1,0,2,3]): not supported [BLAS] 
116s   DUP(type=i16,ne=[10,8,3,1],permute=[0,2,1,3]): not supported [BLAS] 
116s   DUP(type=i16,ne=[10,8,3,1],permute=[1,2,0,3]): not supported [BLAS] 
116s   SET(type_src=f32,type_dst=f32,ne=[6,5,4,3],dim=1): not supported [BLAS] 
116s   SET(type_src=f32,type_dst=f32,ne=[6,5,4,3],dim=2): not supported [BLAS] 
116s   SET(type_src=f32,type_dst=f32,ne=[6,5,4,3],dim=3): not supported [BLAS] 
116s   SET(type_src=i32,type_dst=i32,ne=[6,5,4,3],dim=1): not supported [BLAS] 
116s   SET(type_src=i32,type_dst=i32,ne=[6,5,4,3],dim=2): not supported [BLAS] 
116s   SET(type_src=i32,type_dst=i32,ne=[6,5,4,3],dim=3): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f32,ne=[1,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f32,ne=[1,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f32,ne=[1,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f32,ne=[2,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f32,ne=[2,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f32,ne=[2,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f32,ne=[3,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f32,ne=[3,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f32,ne=[3,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f16,ne=[1,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f16,ne=[1,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f16,ne=[1,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f16,ne=[2,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f16,ne=[2,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f16,ne=[2,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f16,ne=[3,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f16,ne=[3,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f16,ne=[3,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=bf16,ne=[1,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=bf16,ne=[1,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=bf16,ne=[1,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=bf16,ne=[2,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=bf16,ne=[2,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=bf16,ne=[2,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=bf16,ne=[3,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=bf16,ne=[3,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=bf16,ne=[3,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q4_0,type_dst=q4_0,ne=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_0,type_dst=q4_0,ne=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_0,type_dst=q4_0,ne=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q4_0,type_dst=q4_0,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_0,type_dst=q4_0,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_0,type_dst=q4_0,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q4_0,type_dst=q4_0,ne=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_0,type_dst=q4_0,ne=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_0,type_dst=q4_0,ne=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q4_1,type_dst=q4_1,ne=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_1,type_dst=q4_1,ne=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_1,type_dst=q4_1,ne=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q4_1,type_dst=q4_1,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_1,type_dst=q4_1,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_1,type_dst=q4_1,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q4_1,type_dst=q4_1,ne=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_1,type_dst=q4_1,ne=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_1,type_dst=q4_1,ne=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q5_0,type_dst=q5_0,ne=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_0,type_dst=q5_0,ne=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_0,type_dst=q5_0,ne=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q5_0,type_dst=q5_0,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_0,type_dst=q5_0,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_0,type_dst=q5_0,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q5_0,type_dst=q5_0,ne=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_0,type_dst=q5_0,ne=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_0,type_dst=q5_0,ne=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q5_1,type_dst=q5_1,ne=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_1,type_dst=q5_1,ne=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_1,type_dst=q5_1,ne=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q5_1,type_dst=q5_1,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_1,type_dst=q5_1,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_1,type_dst=q5_1,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q5_1,type_dst=q5_1,ne=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_1,type_dst=q5_1,ne=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_1,type_dst=q5_1,ne=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q8_0,type_dst=q8_0,ne=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q8_0,type_dst=q8_0,ne=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q8_0,type_dst=q8_0,ne=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q8_0,type_dst=q8_0,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q8_0,type_dst=q8_0,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q8_0,type_dst=q8_0,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q8_0,type_dst=q8_0,ne=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q8_0,type_dst=q8_0,ne=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q8_0,type_dst=q8_0,ne=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=mxfp4,type_dst=mxfp4,ne=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=mxfp4,type_dst=mxfp4,ne=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=mxfp4,type_dst=mxfp4,ne=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=mxfp4,type_dst=mxfp4,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=mxfp4,type_dst=mxfp4,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=mxfp4,type_dst=mxfp4,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=mxfp4,type_dst=mxfp4,ne=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=mxfp4,type_dst=mxfp4,ne=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=mxfp4,type_dst=mxfp4,ne=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q2_K,type_dst=q2_K,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q2_K,type_dst=q2_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q2_K,type_dst=q2_K,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q2_K,type_dst=q2_K,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q2_K,type_dst=q2_K,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q2_K,type_dst=q2_K,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q2_K,type_dst=q2_K,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q2_K,type_dst=q2_K,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q2_K,type_dst=q2_K,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q3_K,type_dst=q3_K,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q3_K,type_dst=q3_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q3_K,type_dst=q3_K,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q3_K,type_dst=q3_K,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q3_K,type_dst=q3_K,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q3_K,type_dst=q3_K,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q3_K,type_dst=q3_K,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q3_K,type_dst=q3_K,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q3_K,type_dst=q3_K,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q4_K,type_dst=q4_K,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_K,type_dst=q4_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_K,type_dst=q4_K,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q4_K,type_dst=q4_K,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_K,type_dst=q4_K,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_K,type_dst=q4_K,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q4_K,type_dst=q4_K,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_K,type_dst=q4_K,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_K,type_dst=q4_K,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q5_K,type_dst=q5_K,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_K,type_dst=q5_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_K,type_dst=q5_K,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q5_K,type_dst=q5_K,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_K,type_dst=q5_K,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_K,type_dst=q5_K,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q5_K,type_dst=q5_K,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_K,type_dst=q5_K,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_K,type_dst=q5_K,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q6_K,type_dst=q6_K,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q6_K,type_dst=q6_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q6_K,type_dst=q6_K,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q6_K,type_dst=q6_K,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q6_K,type_dst=q6_K,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q6_K,type_dst=q6_K,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=q6_K,type_dst=q6_K,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q6_K,type_dst=q6_K,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q6_K,type_dst=q6_K,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq2_xxs,type_dst=iq2_xxs,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xxs,type_dst=iq2_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xxs,type_dst=iq2_xxs,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq2_xxs,type_dst=iq2_xxs,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xxs,type_dst=iq2_xxs,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xxs,type_dst=iq2_xxs,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq2_xxs,type_dst=iq2_xxs,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xxs,type_dst=iq2_xxs,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xxs,type_dst=iq2_xxs,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq2_xs,type_dst=iq2_xs,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xs,type_dst=iq2_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xs,type_dst=iq2_xs,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq2_xs,type_dst=iq2_xs,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xs,type_dst=iq2_xs,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xs,type_dst=iq2_xs,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq2_xs,type_dst=iq2_xs,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xs,type_dst=iq2_xs,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xs,type_dst=iq2_xs,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq2_s,type_dst=iq2_s,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_s,type_dst=iq2_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_s,type_dst=iq2_s,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq2_s,type_dst=iq2_s,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_s,type_dst=iq2_s,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_s,type_dst=iq2_s,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq2_s,type_dst=iq2_s,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_s,type_dst=iq2_s,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_s,type_dst=iq2_s,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq3_xxs,type_dst=iq3_xxs,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_xxs,type_dst=iq3_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_xxs,type_dst=iq3_xxs,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq3_xxs,type_dst=iq3_xxs,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_xxs,type_dst=iq3_xxs,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_xxs,type_dst=iq3_xxs,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq3_xxs,type_dst=iq3_xxs,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_xxs,type_dst=iq3_xxs,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_xxs,type_dst=iq3_xxs,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq1_s,type_dst=iq1_s,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_s,type_dst=iq1_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_s,type_dst=iq1_s,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq1_s,type_dst=iq1_s,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_s,type_dst=iq1_s,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_s,type_dst=iq1_s,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq1_s,type_dst=iq1_s,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_s,type_dst=iq1_s,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_s,type_dst=iq1_s,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq1_m,type_dst=iq1_m,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_m,type_dst=iq1_m,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_m,type_dst=iq1_m,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq1_m,type_dst=iq1_m,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_m,type_dst=iq1_m,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_m,type_dst=iq1_m,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq1_m,type_dst=iq1_m,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_m,type_dst=iq1_m,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_m,type_dst=iq1_m,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq4_nl,type_dst=iq4_nl,ne=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_nl,type_dst=iq4_nl,ne=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_nl,type_dst=iq4_nl,ne=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq4_nl,type_dst=iq4_nl,ne=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_nl,type_dst=iq4_nl,ne=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_nl,type_dst=iq4_nl,ne=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq4_nl,type_dst=iq4_nl,ne=[96,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_nl,type_dst=iq4_nl,ne=[96,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_nl,type_dst=iq4_nl,ne=[96,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq3_s,type_dst=iq3_s,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_s,type_dst=iq3_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_s,type_dst=iq3_s,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq3_s,type_dst=iq3_s,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_s,type_dst=iq3_s,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_s,type_dst=iq3_s,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq3_s,type_dst=iq3_s,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_s,type_dst=iq3_s,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_s,type_dst=iq3_s,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq4_xs,type_dst=iq4_xs,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_xs,type_dst=iq4_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_xs,type_dst=iq4_xs,ne=[256,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq4_xs,type_dst=iq4_xs,ne=[512,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_xs,type_dst=iq4_xs,ne=[512,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_xs,type_dst=iq4_xs,ne=[512,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=iq4_xs,type_dst=iq4_xs,ne=[768,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_xs,type_dst=iq4_xs,ne=[768,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_xs,type_dst=iq4_xs,ne=[768,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f16,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f16,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=bf16,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=bf16,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q4_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q4_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q4_1,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q4_1,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q5_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q5_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q5_1,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q5_1,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q8_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q8_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=mxfp4,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=mxfp4,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q2_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q2_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q3_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q3_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q4_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q4_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q5_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q5_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q6_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=q6_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq2_xxs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq2_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq2_xs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq2_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq2_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq2_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq3_xxs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq3_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq1_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq1_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq1_m,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq1_m,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq4_nl,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq4_nl,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq3_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq3_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq4_xs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=iq4_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=f16,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=f16,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=bf16,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=bf16,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q4_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q4_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q4_1,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q4_1,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q5_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q5_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q5_1,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q5_1,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q8_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q8_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=mxfp4,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=mxfp4,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q2_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q2_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q3_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q3_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q4_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q4_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q5_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q5_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q6_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=q6_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq2_xxs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq2_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq2_xs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq2_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq2_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq2_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq3_xxs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq3_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq1_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq1_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq1_m,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq1_m,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq4_nl,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq4_nl,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq3_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq3_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq4_xs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=iq4_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f16,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f16,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=bf16,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=bf16,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q4_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q4_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q4_1,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q4_1,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q5_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q5_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q5_1,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q5_1,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q8_0,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q8_0,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=mxfp4,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=mxfp4,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q2_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q2_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q3_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q3_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q4_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q4_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q5_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q5_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q6_K,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=q6_K,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq2_xxs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq2_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq2_xs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq2_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq2_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq2_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq3_xxs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq3_xxs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq1_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq1_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq1_m,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq1_m,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq4_nl,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq4_nl,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq3_s,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq3_s,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq4_xs,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=iq4_xs,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=bf16,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_0,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_0,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_1,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_1,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_0,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_0,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_1,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_1,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q8_0,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q8_0,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=mxfp4,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=mxfp4,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q2_K,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q2_K,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q3_K,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q3_K,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_K,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q4_K,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_K,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q5_K,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q6_K,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=q6_K,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xxs,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xxs,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xs,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_xs,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_s,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq2_s,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_xxs,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_xxs,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_s,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_s,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_m,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq1_m,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_nl,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_nl,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_s,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq3_s,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_xs,type_dst=f32,ne=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=iq4_xs,type_dst=f32,ne=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f16,ne=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f16,type_dst=f32,ne=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f16,ne=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=f32,ne=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=i32,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=f32,type_dst=i32,ne=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=i32,type_dst=f32,ne=[256,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CPY(type_src=i32,type_dst=f32,ne=[256,2,3,4],permute_src=[1,0,2,3],permute_dst=[0,0,0,0]): not supported [BLAS] 
116s   CONT(type=f32,ne=[10,10,10,1]): not supported [BLAS] 
116s   CONT(type=f32,ne=[2,1,1,1]): not supported [BLAS] 
116s   CONT(type=f32,ne=[2,1,3,5]): not supported [BLAS] 
116s   CONT(type=f32,ne=[2,3,5,7]): not supported [BLAS] 
116s   CONT(type=f16,ne=[2,1,1,1]): not supported [BLAS] 
116s   CONT(type=f16,ne=[2,1,3,5]): not supported [BLAS] 
116s   CONT(type=f16,ne=[2,3,5,7]): not supported [BLAS] 
116s   CONT(type=bf16,ne=[2,1,1,1]): not supported [BLAS] 
116s   CONT(type=bf16,ne=[2,1,3,5]): not supported [BLAS] 
116s   CONT(type=bf16,ne=[2,3,5,7]): not supported [BLAS] 
116s   ADD(type=f16,ne=[1,1,8,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[1,1,8,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[1,1,8,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[1,1,8,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[1,1,1,1],nr=[32,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[1,1,1,1],nr=[32,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[1,1,1,1],nr=[32,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[1,1,1,1],nr=[32,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[1,1,320,320],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[1,1,320,320],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[1,1,320,320],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[1,1,320,320],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[10,5,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[10,5,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[10,5,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[10,5,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[10,5,4,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[10,5,4,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[10,5,4,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[10,5,4,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[10,5,4,3],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[10,5,4,3],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[10,5,4,3],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[10,5,4,3],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[10,5,4,3],nr=[2,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[10,5,4,3],nr=[2,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[10,5,4,3],nr=[2,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[10,5,4,3],nr=[2,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[10,5,4,3],nr=[1,2,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[10,5,4,3],nr=[1,2,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[10,5,4,3],nr=[1,2,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[10,5,4,3],nr=[1,2,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[10,5,4,3],nr=[1,1,2,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[10,5,4,3],nr=[1,1,2,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[10,5,4,3],nr=[1,1,2,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[10,5,4,3],nr=[1,1,2,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[10,5,4,3],nr=[1,1,1,2],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[10,5,4,3],nr=[1,1,1,2],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[10,5,4,3],nr=[1,1,1,2],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[10,5,4,3],nr=[1,1,1,2],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[10,5,4,3],nr=[1,1,2,2],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[10,5,4,3],nr=[1,1,2,2],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[10,5,4,3],nr=[1,1,2,2],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[10,5,4,3],nr=[1,1,2,2],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[10,5,4,3],nr=[1,2,2,2],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[10,5,4,3],nr=[1,2,2,2],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[10,5,4,3],nr=[1,2,2,2],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[10,5,4,3],nr=[1,2,2,2],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[10,5,4,3],nr=[2,2,2,2],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[10,5,4,3],nr=[2,2,2,2],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[10,5,4,3],nr=[2,2,2,2],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[10,5,4,3],nr=[2,2,2,2],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[1,1,65536,1],nr=[256,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[1,1,65536,1],nr=[256,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[1,1,65536,1],nr=[256,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[1,1,65536,1],nr=[256,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[1280,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[1280,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[1280,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[1280,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[1280,1,1,1],nr=[1,16,16,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[1280,1,1,1],nr=[1,16,16,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[1280,1,1,1],nr=[1,16,16,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[1280,1,1,1],nr=[1,16,16,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[1280,16,16,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[1280,16,16,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[1280,16,16,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[1280,16,16,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[1280,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[1280,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[1280,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[1280,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[1,1,1280,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[1,1,1280,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[1,1,1280,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[1,1,1280,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[16,16,1280,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[16,16,1280,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[16,16,1280,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[16,16,1280,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[1,1,1920,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[1,1,1920,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[1,1,1920,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[1,1,1920,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[1,1,2560,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[1,1,2560,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[1,1,2560,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[1,1,2560,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[1,1,1280,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[1,1,1280,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[1,1,1280,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[1,1,1280,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[1,1,1920,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[1,1,1920,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[1,1,1920,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[1,1,1920,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[1,1,640,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[1,1,640,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[1,1,640,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[1,1,640,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[5120,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[5120,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[5120,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[5120,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f16,ne=[640,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f16,ne=[640,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f16,ne=[640,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f16,ne=[640,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[1,1,8,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[1,1,8,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[1,1,8,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[1,1,8,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[1,1,1,1],nr=[32,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[1,1,1,1],nr=[32,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[1,1,1,1],nr=[32,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[1,1,1,1],nr=[32,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[1,1,320,320],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[1,1,320,320],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[1,1,320,320],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[1,1,320,320],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[10,5,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[10,5,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[10,5,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[10,5,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[10,5,4,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[10,5,4,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[10,5,4,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[10,5,4,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[10,5,4,3],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[10,5,4,3],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[10,5,4,3],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[10,5,4,3],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[10,5,4,3],nr=[2,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[10,5,4,3],nr=[2,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[10,5,4,3],nr=[2,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[10,5,4,3],nr=[2,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[10,5,4,3],nr=[1,2,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[10,5,4,3],nr=[1,2,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[10,5,4,3],nr=[1,2,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[10,5,4,3],nr=[1,2,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[10,5,4,3],nr=[1,1,2,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[10,5,4,3],nr=[1,1,2,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[10,5,4,3],nr=[1,1,2,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[10,5,4,3],nr=[1,1,2,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[10,5,4,3],nr=[1,1,1,2],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[10,5,4,3],nr=[1,1,1,2],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[10,5,4,3],nr=[1,1,1,2],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[10,5,4,3],nr=[1,1,1,2],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[10,5,4,3],nr=[1,1,2,2],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[10,5,4,3],nr=[1,1,2,2],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[10,5,4,3],nr=[1,1,2,2],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[10,5,4,3],nr=[1,1,2,2],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[10,5,4,3],nr=[1,2,2,2],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[10,5,4,3],nr=[1,2,2,2],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[10,5,4,3],nr=[1,2,2,2],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[10,5,4,3],nr=[1,2,2,2],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[10,5,4,3],nr=[2,2,2,2],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[10,5,4,3],nr=[2,2,2,2],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[10,5,4,3],nr=[2,2,2,2],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[10,5,4,3],nr=[2,2,2,2],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[1,1,65536,1],nr=[256,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[1,1,65536,1],nr=[256,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[1,1,65536,1],nr=[256,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[1,1,65536,1],nr=[256,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[1280,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[1280,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[1280,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[1280,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[1280,1,1,1],nr=[1,16,16,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[1280,1,1,1],nr=[1,16,16,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[1280,1,1,1],nr=[1,16,16,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[1280,1,1,1],nr=[1,16,16,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[1280,16,16,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[1280,16,16,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[1280,16,16,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[1280,16,16,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[1280,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[1280,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[1280,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[1280,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[1,1,1280,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[1,1,1280,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[1,1,1280,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[1,1,1280,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[16,16,1280,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[16,16,1280,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[16,16,1280,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[16,16,1280,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[1,1,1920,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[1,1,1920,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[1,1,1920,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[1,1,1920,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[1,1,2560,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[1,1,2560,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[1,1,2560,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[1,1,2560,1],nr=[16,16,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[1,1,1280,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[1,1,1280,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[1,1,1280,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[1,1,1280,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[1,1,1920,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[1,1,1920,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[1,1,1920,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[1,1,1920,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[1,1,640,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[1,1,640,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[1,1,640,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[1,1,640,1],nr=[32,32,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[5120,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[5120,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[5120,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[5120,1,1,1],nr=[1,256,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[640,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   SUB(type=f32,ne=[640,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   MUL(type=f32,ne=[640,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   DIV(type=f32,ne=[640,1,1,1],nr=[1,1,1,1],nf=1): not supported [BLAS] 
116s   ADD(type=f32,ne=[16,5,4,3],nr=[1,1,1,1],nf=16): not supported [BLAS] 
116s   MUL(type=f32,ne=[16,5,4,3],nr=[1,1,1,1],nf=16): not supported [BLAS] 
116s   ADD(type=f32,ne=[10,5,4,3],nr=[2,1,1,1],nf=2): not supported [BLAS] 
116s   ADD(type=f32,ne=[16,5,4,3],nr=[1,2,1,1],nf=3): not supported [BLAS] 
116s   ADD(type=f32,ne=[10,5,4,3],nr=[1,1,2,1],nf=4): not supported [BLAS] 
116s   ADD(type=f32,ne=[16,5,4,3],nr=[1,1,1,2],nf=5): not supported [BLAS] 
116s   ADD(type=f32,ne=[10,5,4,3],nr=[1,1,2,2],nf=6): not supported [BLAS] 
116s   ADD(type=f32,ne=[10,5,4,3],nr=[1,2,2,2],nf=7): not supported [BLAS] 
116s   ADD(type=f32,ne=[16,5,4,3],nr=[2,2,2,2],nf=8): not supported [BLAS] 
116s   ADD(type=f32,ne=[16,5,4,3],nr=[1,1,1,1],nf=16): not supported [BLAS] 
116s   ADD1(type=f32,ne=[10,5,4,3]): not supported [BLAS] 
116s   SCALE(type=f32,ne=[10,10,10,10],scale=2.000000,bias=0.000000): not supported [BLAS] 
116s   SCALE(type=f32,ne=[10,10,10,10],scale=2.000000,bias=1.000000): not supported [BLAS] 
116s   SCALE(type=f32,ne=[100,10,10,10],scale=2.000000,bias=1.000000): not supported [BLAS] 
116s   SOFTCAP(type=f32,ne=[10,10,10,10],softcap=50.000000): not supported [BLAS] 
116s   SILU_BACK(type=f32,ne=[64,5,4,3],eps=0.000001): not supported [BLAS] 
116s   NORM(type=f32,ne=[64,5,4,3],v=0,eps=0.000000): not supported [BLAS] 
116s   RMS_NORM(type=f32,ne=[64,5,4,3],v=0,eps=0.000000): not supported [BLAS] 
116s   NORM(type=f32,ne=[64,5,4,3],v=1,eps=0.000000): not supported [BLAS] 
116s   RMS_NORM(type=f32,ne=[64,5,4,3],v=1,eps=0.000000): not supported [BLAS] 
116s   RMS_NORM_BACK(type=f32,ne=[64,5,4,3],eps=0.000000): not supported [BLAS] 
116s   L2_NORM(type=f32,ne=[64,5,4,3]): not supported [BLAS] 
116s   NORM(type=f32,ne=[64,5,4,3],v=0,eps=0.000001): not supported [BLAS] 
116s   RMS_NORM(type=f32,ne=[64,5,4,3],v=0,eps=0.000001): not supported [BLAS] 
116s   NORM(type=f32,ne=[64,5,4,3],v=1,eps=0.000001): not supported [BLAS] 
116s   RMS_NORM(type=f32,ne=[64,5,4,3],v=1,eps=0.000001): not supported [BLAS] 
116s   RMS_NORM_BACK(type=f32,ne=[64,5,4,3],eps=0.000001): not supported [BLAS] 
116s   L2_NORM(type=f32,ne=[64,5,4,3]): not supported [BLAS] 
116s   NORM(type=f32,ne=[64,5,4,3],v=0,eps=0.000100): not supported [BLAS] 
116s   RMS_NORM(type=f32,ne=[64,5,4,3],v=0,eps=0.000100): not supported [BLAS] 
116s   NORM(type=f32,ne=[64,5,4,3],v=1,eps=0.000100): not supported [BLAS] 
116s   RMS_NORM(type=f32,ne=[64,5,4,3],v=1,eps=0.000100): not supported [BLAS] 
116s   RMS_NORM_BACK(type=f32,ne=[64,5,4,3],eps=0.000100): not supported [BLAS] 
116s   L2_NORM(type=f32,ne=[64,5,4,3]): not supported [BLAS] 
116s   NORM(type=f32,ne=[64,5,4,3],v=0,eps=0.100000): not supported [BLAS] 
116s   RMS_NORM(type=f32,ne=[64,5,4,3],v=0,eps=0.100000): not supported [BLAS] 
116s   NORM(type=f32,ne=[64,5,4,3],v=1,eps=0.100000): not supported [BLAS] 
116s   RMS_NORM(type=f32,ne=[64,5,4,3],v=1,eps=0.100000): not supported [BLAS] 
116s   RMS_NORM_BACK(type=f32,ne=[64,5,4,3],eps=0.100000): not supported [BLAS] 
116s   L2_NORM(type=f32,ne=[64,5,4,3]): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.000000,broadcast=0,multi_add=0): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.000000,broadcast=1,multi_add=0): not supported [BLAS] 
116s   NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.000000,broadcast=0): not supported [BLAS] 
116s   NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.000000,broadcast=1): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.000001,broadcast=0,multi_add=0): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.000001,broadcast=1,multi_add=0): not supported [BLAS] 
116s   NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.000001,broadcast=0): not supported [BLAS] 
116s   NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.000001,broadcast=1): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.000100,broadcast=0,multi_add=0): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.000100,broadcast=1,multi_add=0): not supported [BLAS] 
116s   NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.000100,broadcast=0): not supported [BLAS] 
116s   NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.000100,broadcast=1): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.100000,broadcast=0,multi_add=0): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.100000,broadcast=1,multi_add=0): not supported [BLAS] 
116s   NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.100000,broadcast=0): not supported [BLAS] 
116s   NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=0.100000,broadcast=1): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=1.000000,broadcast=0,multi_add=0): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=1.000000,broadcast=1,multi_add=0): not supported [BLAS] 
116s   NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=1.000000,broadcast=0): not supported [BLAS] 
116s   NORM_MUL_ADD(type=f32,ne=[64,5,4,3],eps=1.000000,broadcast=1): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[1,1,1,1],eps=0.000001,broadcast=0,multi_add=0): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[1,1,1,1],eps=0.000001,broadcast=0,multi_add=1): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[511,1,1,1],eps=0.000001,broadcast=0,multi_add=0): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[511,1,1,1],eps=0.000001,broadcast=0,multi_add=1): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[1025,1,1,1],eps=0.000001,broadcast=0,multi_add=0): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[1025,1,1,1],eps=0.000001,broadcast=0,multi_add=1): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[8192,1,1,1],eps=0.000001,broadcast=0,multi_add=0): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[8192,1,1,1],eps=0.000001,broadcast=0,multi_add=1): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[16896,1,1,1],eps=0.000001,broadcast=0,multi_add=0): not supported [BLAS] 
116s   RMS_NORM_MUL_ADD(type=f32,ne=[16896,1,1,1],eps=0.000001,broadcast=0,multi_add=1): not supported [BLAS] 
116s   L2_NORM(type=f32,ne=[64,5,4,3]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[4,1024,1,1],ne_b=[3,1024,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[8,1024,1,1],ne_b=[3,1024,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[4,1024,4,1],ne_b=[3,1024,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[4,1536,1,1],ne_b=[3,1536,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[8,1536,1,1],ne_b=[3,1536,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[4,1536,4,1],ne_b=[3,1536,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[4,2048,1,1],ne_b=[3,2048,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[8,2048,1,1],ne_b=[3,2048,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[4,2048,4,1],ne_b=[3,2048,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[4,1024,1,1],ne_b=[4,1024,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[8,1024,1,1],ne_b=[4,1024,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[4,1024,4,1],ne_b=[4,1024,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[4,1536,1,1],ne_b=[4,1536,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[8,1536,1,1],ne_b=[4,1536,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[4,1536,4,1],ne_b=[4,1536,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[4,2048,1,1],ne_b=[4,2048,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[8,2048,1,1],ne_b=[4,2048,1,1]): not supported [BLAS] 
116s   SSM_CONV(type=f32,ne_a=[4,2048,4,1],ne_b=[4,2048,1,1]): not supported [BLAS] 
116s   SSM_SCAN(type=f32,d_state=16,head_dim=1,n_head=1024,n_group=1,n_seq_tokens=32,n_seqs=4): not supported [BLAS] 
116s   SSM_SCAN(type=f32,d_state=128,head_dim=64,n_head=16,n_group=2,n_seq_tokens=32,n_seqs=4): not supported [BLAS] 
116s   SSM_SCAN(type=f32,d_state=256,head_dim=64,n_head=8,n_group=2,n_seq_tokens=32,n_seqs=4): not supported [BLAS] 
116s   RWKV_WKV6(type=f32,head_count=32,head_size=64,n_seq_tokens=1,n_seqs=1): not supported [BLAS] 
116s   RWKV_WKV6(type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=1): not supported [BLAS] 
116s   RWKV_WKV6(type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=4): not supported [BLAS] 
116s   RWKV_WKV6(type=f32,head_count=32,head_size=64,n_seq_tokens=128,n_seqs=4): not supported [BLAS] 
116s   RWKV_WKV7(type=f32,head_count=32,head_size=64,n_seq_tokens=1,n_seqs=1): not supported [BLAS] 
116s   RWKV_WKV7(type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=1): not supported [BLAS] 
116s   RWKV_WKV7(type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=4): not supported [BLAS] 
116s   RWKV_WKV7(type=f32,head_count=32,head_size=64,n_seq_tokens=128,n_seqs=4): not supported [BLAS] 
116s   GATED_LINEAR_ATTN(type=f32,head_count=32,head_size=64,n_seq_tokens=1,n_seqs=1): not supported [BLAS] 
116s   GATED_LINEAR_ATTN(type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=1): not supported [BLAS] 
116s   GATED_LINEAR_ATTN(type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=4): not supported [BLAS] 
116s   GATED_LINEAR_ATTN(type=f32,head_count=32,head_size=64,n_seq_tokens=128,n_seqs=4): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_0,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_0,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_0,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_0,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_0,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_0,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_0,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_0,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_1,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_1,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_1,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_1,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_1,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_1,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_1,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_1,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_1,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q2_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q2_K,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q2_K,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q2_K,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q2_K,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q2_K,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q2_K,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q2_K,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q2_K,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q3_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q3_K,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q3_K,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q3_K,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q3_K,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q3_K,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q3_K,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q3_K,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q3_K,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_K,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_K,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_K,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_K,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_K,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_K,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_K,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_K,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q6_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q6_K,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q6_K,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q6_K,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q6_K,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q6_K,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q6_K,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q6_K,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q6_K,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xs,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xs,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xs,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xs,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xs,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xs,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xs,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xs,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xs,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_s,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_s,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_s,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_s,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_s,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_s,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_s,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_s,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_s,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_xxs,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_xxs,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_xxs,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_xxs,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_xxs,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_xxs,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_xxs,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_xxs,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_xxs,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_s,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_s,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_s,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_s,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_s,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_s,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_s,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_s,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_s,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_m,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_m,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_m,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_m,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_m,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_m,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_m,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_m,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_m,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_nl,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_nl,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_nl,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_nl,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_nl,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_nl,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_nl,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_nl,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_nl,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_s,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_s,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_s,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_s,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_s,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_s,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_s,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_s,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_s,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_xs,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_xs,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_xs,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_xs,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_xs,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_xs,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_xs,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_xs,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_xs,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f16,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f16,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f16,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f32,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_0,type_b=f16,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f16,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f32,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_K,type_b=f16,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f32,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=mxfp4,type_b=f16,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f32,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xxs,type_b=f16,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=32,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_0,type_b=f32,m=16,n=1,k=32,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_1,type_b=f32,m=16,n=1,k=32,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_1,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=32,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q2_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q3_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q5_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=q6_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_xs,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq2_s,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_xxs,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_s,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq1_m,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_nl,type_b=f32,m=16,n=1,k=32,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_nl,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq3_s,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=iq4_xs,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=16,n=1,k=1,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=64,n=2,k=128,bs=[8,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=83,n=2,k=128,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=64,n=2,k=64,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=83,n=2,k=64,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=64,n=45,k=128,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=0,o=1): OK
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=45,k=64,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=0,o=1): OK
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=193,bs=[1,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=67,bs=[1,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=16,n=32,k=32,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=1,o=3): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=64,n=77,k=77,bs=[12,1],nr=[1,1],per=[0,1,2,3],v=0,o=1): OK
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[1,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[1,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[1,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[1,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[1,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[1,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[1,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[1,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[1,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[1,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[1,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[1,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[1,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[1,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[1,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[1,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[1,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[1,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[1,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[1,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[1,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[1,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[1,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[1,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[1,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[1,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[1,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[1,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[1,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[1,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[1,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[1,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[1,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[1,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[1,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[1,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[1,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[2,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[2,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[2,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[2,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[2,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[2,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[2,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[2,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[2,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[2,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[2,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[2,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[2,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[2,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[2,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[2,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[2,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[2,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[2,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[2,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[2,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[2,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[2,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[2,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[2,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[2,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[2,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[2,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[2,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[2,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[2,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[2,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[2,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[2,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[2,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[2,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[2,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[2,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[2,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[2,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[2,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[2,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[2,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[2,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[2,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[2,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[2,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[2,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[4,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[4,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[4,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[4,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[4,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[4,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[4,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[4,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[4,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[4,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[4,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[4,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[4,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[4,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[4,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[4,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[4,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[4,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[4,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[4,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[4,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[4,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[4,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[4,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[4,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[4,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[4,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[4,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[4,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[4,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[4,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[4,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[4,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[4,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[4,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[4,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[4,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[4,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[4,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[4,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[4,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[4,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[4,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[4,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[4,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[4,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[4,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[4,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[8,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[8,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[8,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[8,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[8,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[8,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[8,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[8,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[8,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[8,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[8,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[8,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[8,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[8,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[8,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[8,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[8,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[8,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[8,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[8,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[8,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[8,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[8,1],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[8,1],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[8,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[8,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[8,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[8,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[8,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[8,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[8,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[8,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[8,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[8,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[8,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[8,1],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[8,1],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[1,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[1,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[1,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[1,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[1,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[1,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[1,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[1,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[1,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[1,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[1,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[1,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[1,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[1,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[1,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[1,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[1,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[1,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[1,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[1,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[1,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[1,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[1,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[1,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[1,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[1,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[1,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[1,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[1,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[1,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[1,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[1,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[1,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[1,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[1,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[1,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[1,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[1,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[1,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[1,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[1,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[1,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[1,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[1,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[1,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[1,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[1,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[1,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[2,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[2,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[2,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[2,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[2,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[2,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[2,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[2,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[2,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[2,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[2,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[2,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[2,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[2,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[2,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[2,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[2,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[2,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[2,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[2,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[2,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[2,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[2,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[2,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[2,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[2,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[2,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[2,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[2,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[2,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[2,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[2,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[2,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[2,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[2,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[2,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[2,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[4,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[4,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[4,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[4,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[4,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[4,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[4,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[4,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[4,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[4,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[4,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[4,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[4,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[4,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[4,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[4,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[4,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[4,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[4,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[4,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[4,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[4,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[4,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[4,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[4,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[4,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[4,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[4,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[4,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[4,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[4,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[4,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[4,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[4,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[4,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[4,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[4,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[4,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[4,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[4,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[4,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[4,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[4,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[4,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[4,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[4,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[4,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[4,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[8,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[8,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[8,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[8,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[8,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[8,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[8,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[8,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[8,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[8,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[8,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[8,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[8,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[8,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[8,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[8,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[8,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[8,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[8,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[8,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[8,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[8,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[8,3],nr=[1,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[8,3],nr=[1,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=128,bs=[8,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1056,bs=[8,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=128,bs=[8,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1056,bs=[8,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=128,bs=[8,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1056,bs=[8,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1056,n=1,k=129,bs=[8,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=128,n=1,k=1057,bs=[8,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1056,n=1,k=129,bs=[8,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=128,n=1,k=1057,bs=[8,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1056,n=1,k=129,bs=[8,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=128,n=1,k=1057,bs=[8,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=128,bs=[8,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1056,bs=[8,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=128,bs=[8,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1056,bs=[8,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=128,bs=[8,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1056,bs=[8,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=1057,n=1,k=129,bs=[8,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f16,type_b=f32,m=129,n=1,k=1057,bs=[8,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=1057,n=1,k=129,bs=[8,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=bf16,type_b=f32,m=129,n=1,k=1057,bs=[8,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=1057,n=1,k=129,bs=[8,3],nr=[4,1],per=[0,2,1,3],v=0,o=1): not supported [BLAS] 
116s   MUL_MAT(type_a=f32,type_b=f32,m=129,n=1,k=1057,bs=[8,3],nr=[4,1],per=[0,1,2,3],v=1,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=16,n_used=16,b=0,m=32,n=1024,k=16,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=2,n_used=2,b=0,m=32,n=8192,k=64,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=16,n_used=16,b=0,m=50,n=200,k=64,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=16,n_used=16,b=1,m=32,n=1024,k=16,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=2,n_used=2,b=1,m=32,n=8192,k=64,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=16,n_used=16,b=1,m=50,n=200,k=64,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=1,n_used=1,b=0,m=8,n=16,k=1,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=16,n_used=16,b=0,m=32,n=32,k=32,o=3): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f32,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=f16,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_K,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=mxfp4,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=4,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=5,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xxs,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q5_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q5_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q5_1,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q5_1,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q2_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q2_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q3_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q3_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q5_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q5_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q6_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=q6_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xs,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_xs,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_s,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq2_s,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq3_xxs,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq3_xxs,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq1_s,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq1_s,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq1_m,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq1_m,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq4_nl,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq4_nl,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq3_s,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq3_s,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq4_xs,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=iq4_xs,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=bf16,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256,o=1): not supported [BLAS] 
116s   MUL_MAT_ID(type_a=bf16,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256,o=1): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): OK
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): OK
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): OK
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): OK
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f32,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=f16,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q8_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_1,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=q4_K,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=mxfp4,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0): not supported [BLAS] 
116s   OUT_PROD(type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=1,n_token=1): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=1,n_token=32): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=1,n_token=129): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=4,n_experts_used=1,n_token=1): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=4,n_experts_used=1,n_token=32): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=4,n_experts_used=1,n_token=129): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=2,n_token=1): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=2,n_token=32): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=2,n_token=129): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=4,n_experts_used=2,n_token=1): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=4,n_experts_used=2,n_token=32): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=4,n_experts_used=2,n_token=129): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=4,n_token=1): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=4,n_token=32): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=4,n_token=129): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=4,n_experts_used=4,n_token=1): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=4,n_experts_used=4,n_token=32): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=4,n_experts_used=4,n_token=129): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=8,n_experts_used=1,n_token=1): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=8,n_experts_used=1,n_token=32): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=8,n_experts_used=1,n_token=129): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=1,n_token=1): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=1,n_token=32): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=1,n_token=129): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=8,n_experts_used=2,n_token=1): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=8,n_experts_used=2,n_token=32): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=8,n_experts_used=2,n_token=129): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=2,n_token=1): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=2,n_token=32): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=2,n_token=129): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=8,n_experts_used=4,n_token=1): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=8,n_experts_used=4,n_token=32): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=32,n_experts=8,n_experts_used=4,n_token=129): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=4,n_token=1): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=4,n_token=32): not supported [BLAS] 
116s   ADD_ID(type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=4,n_token=129): not supported [BLAS] 
116s   SQR(type=f16,ne=[10,5,4,3]): not supported [BLAS] 
116s   SQRT(type=f16,ne=[10,3,3,2]): not supported [BLAS] 
116s   LOG(type=f16,ne=[10,5,4,3]): not supported [BLAS] 
116s   SIN(type=f16,ne=[10,2,2,2]): not supported [BLAS] 
116s   COS(type=f16,ne=[10,2,2,2]): not supported [BLAS] 
116s   CLAMP(type=f16,ne=[10,5,4,3],min=-0.500000,max=0.500000): not supported [BLAS] 
116s   LEAKY_RELU(type=f16,ne_a=[10,5,4,3],negative_slope=0.100000): not supported [BLAS] 
116s   SQR(type=f16,ne=[7,1,5,3]): not supported [BLAS] 
116s   SQRT(type=f16,ne=[7,1,5,3]): not supported [BLAS] 
116s   LOG(type=f16,ne=[7,1,5,3]): not supported [BLAS] 
116s   SIN(type=f16,ne=[7,1,5,3]): not supported [BLAS] 
116s   COS(type=f16,ne=[7,1,5,3]): not supported [BLAS] 
116s   CLAMP(type=f16,ne=[7,1,5,3],min=-0.500000,max=0.500000): not supported [BLAS] 
116s   LEAKY_RELU(type=f16,ne_a=[7,1,5,3],negative_slope=0.100000): not supported [BLAS] 
116s   SQR(type=f32,ne=[10,5,4,3]): not supported [BLAS] 
116s   SQRT(type=f32,ne=[10,3,3,2]): not supported [BLAS] 
116s   LOG(type=f32,ne=[10,5,4,3]): not supported [BLAS] 
116s   SIN(type=f32,ne=[10,2,2,2]): not supported [BLAS] 
116s   COS(type=f32,ne=[10,2,2,2]): not supported [BLAS] 
116s   CLAMP(type=f32,ne=[10,5,4,3],min=-0.500000,max=0.500000): not supported [BLAS] 
116s   LEAKY_RELU(type=f32,ne_a=[10,5,4,3],negative_slope=0.100000): not supported [BLAS] 
116s   SQR(type=f32,ne=[7,1,5,3]): not supported [BLAS] 
116s   SQRT(type=f32,ne=[7,1,5,3]): not supported [BLAS] 
116s   LOG(type=f32,ne=[7,1,5,3]): not supported [BLAS] 
116s   SIN(type=f32,ne=[7,1,5,3]): not supported [BLAS] 
116s   COS(type=f32,ne=[7,1,5,3]): not supported [BLAS] 
116s   CLAMP(type=f32,ne=[7,1,5,3],min=-0.500000,max=0.500000): not supported [BLAS] 
116s   LEAKY_RELU(type=f32,ne_a=[7,1,5,3],negative_slope=0.100000): not supported [BLAS] 
116s   DIAG_MASK_INF(type=f32,ne=[10,10,1,1],n_past=5): not supported [BLAS] 
116s   DIAG_MASK_INF(type=f32,ne=[10,10,3,1],n_past=5): not supported [BLAS] 
116s   DIAG_MASK_INF(type=f32,ne=[10,10,3,2],n_past=5): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=0,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=0,m_prec=f32,nr23=[3,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f32,nr23=[2,3],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=0,m_prec=f16,nr23=[3,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f16,nr23=[2,3],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=0,m_prec=f32,nr23=[3,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f32,nr23=[2,3],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=0,m_prec=f16,nr23=[3,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f16,nr23=[2,3],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=0,m_prec=f32,nr23=[3,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f32,nr23=[2,3],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=0,m_prec=f16,nr23=[3,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f16,nr23=[2,3],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=0,m_prec=f32,nr23=[3,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f32,nr23=[2,3],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=0,m_prec=f16,nr23=[3,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=0,m_prec=f16,nr23=[2,3],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=0,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=1,m_prec=f32,nr23=[3,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f32,nr23=[2,3],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=1,m_prec=f16,nr23=[3,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f16,nr23=[2,3],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=1,m_prec=f32,nr23=[3,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f32,nr23=[2,3],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=1,m_prec=f16,nr23=[3,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f16,nr23=[2,3],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=1,m_prec=f32,nr23=[3,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f32,nr23=[2,3],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=1,m_prec=f16,nr23=[3,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f16,nr23=[2,3],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=1,m_prec=f32,nr23=[3,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f32,nr23=[2,3],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,16,1,3],mask=1,sinks=1,m_prec=f16,nr23=[3,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,15,1,1],mask=1,sinks=1,m_prec=f16,nr23=[2,3],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,1024,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[15,1023,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,16,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,15,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1024,1024,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[1023,1023,1,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,2,32,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,2,32,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[16,2,32,1],mask=0,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[32,2,32,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[32,2,32,1],mask=1,sinks=0,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[32,2,32,1],mask=1,sinks=1,m_prec=f32,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX(type=f32,ne=[32,2,32,1],mask=1,sinks=1,m_prec=f16,nr23=[1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,16,1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[15,15,1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,16,2,3],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,1024,1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[15,1023,1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,1024,2,3],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,16,1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1023,15,1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,16,2,3],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,1024,1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1023,1023,1,1],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,1024,2,3],scale=1.000000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,16,1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[15,15,1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,16,2,3],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,1024,1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[15,1023,1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,1024,2,3],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,16,1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1023,15,1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,16,2,3],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,1024,1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1023,1023,1,1],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,1024,2,3],scale=0.100000,max_bias=0.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,16,1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[15,15,1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,16,2,3],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,1024,1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[15,1023,1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,1024,2,3],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,16,1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1023,15,1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,16,2,3],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,1024,1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1023,1023,1,1],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,1024,2,3],scale=1.000000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,16,1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[15,15,1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,16,2,3],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,1024,1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[15,1023,1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[16,1024,2,3],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,16,1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1023,15,1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,16,2,3],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,1024,1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1023,1023,1,1],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   SOFT_MAX_BACK(type=f32,ne=[1024,1024,2,3],scale=0.100000,max_bias=8.000000): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,40,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,52,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,64,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,1,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,71,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,8,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,12,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,28,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,12,2,1],n_dims=20,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,28,2,1],n_dims=32,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,16,2,1],n_dims=80,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,40,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,52,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,64,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,1,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,71,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,8,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,12,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,28,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,12,2,1],n_dims=20,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,28,2,1],n_dims=32,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,16,2,1],n_dims=80,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,40,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,52,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,64,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,1,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,71,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,8,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,12,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,28,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,12,2,1],n_dims=20,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,28,2,1],n_dims=32,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,16,2,1],n_dims=80,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,40,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,52,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,64,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,1,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,71,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,8,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,12,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,28,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,12,2,1],n_dims=20,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,28,2,1],n_dims=32,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[80,16,2,1],n_dims=80,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,40,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,52,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,64,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,1,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,71,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,8,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,12,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,28,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,12,2,1],n_dims=20,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,28,2,1],n_dims=32,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,16,2,1],n_dims=80,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,40,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,52,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,64,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,1,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,71,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,8,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,12,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,28,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,12,2,1],n_dims=20,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,28,2,1],n_dims=32,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,16,2,1],n_dims=80,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,40,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,52,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,64,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,1,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,71,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,8,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,12,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,28,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,12,2,1],n_dims=20,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,28,2,1],n_dims=32,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,16,2,1],n_dims=80,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,40,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,52,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,64,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,1,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,71,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,8,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=20,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,2,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,32,4,1],n_dims=32,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,12,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,28,2,1],n_dims=128,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,12,2,1],n_dims=20,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,28,2,1],n_dims=32,mode=8,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[80,16,2,1],n_dims=80,mode=24,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.000000,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.000000,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.000000,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f32,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=0,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=0): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[128,32,2,1],n_dims=128,mode=0,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   ROPE_BACK(type=f16,ne_a=[64,128,2,1],n_dims=64,mode=2,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3): not supported [BLAS] 
116s   CONCAT(type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3): not supported [BLAS] 
116s   CONCAT(type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3): not supported [BLAS] 
116s   ARGSORT(type=f32,ne=[8,1,1,1],order=0): not supported [BLAS] 
116s   ARGSORT(type=f32,ne=[16,10,10,10],order=0): not supported [BLAS] 
116s   ARGSORT(type=f32,ne=[60,10,10,10],order=0): not supported [BLAS] 
116s   ARGSORT(type=f32,ne=[1024,1,1,1],order=0): not supported [BLAS] 
116s   ARGSORT(type=f32,ne=[16384,1,1,1],order=0): not supported [BLAS] 
116s   ARGSORT(type=f32,ne=[8,1,1,1],order=1): not supported [BLAS] 
116s   ARGSORT(type=f32,ne=[16,10,10,10],order=1): not supported [BLAS] 
116s   ARGSORT(type=f32,ne=[60,10,10,10],order=1): not supported [BLAS] 
116s   ARGSORT(type=f32,ne=[1024,1,1,1],order=1): not supported [BLAS] 
116s   ARGSORT(type=f32,ne=[16384,1,1,1],order=1): not supported [BLAS] 
116s   UPSCALE(type=f32,ne=[512,512,3,2],scale_factor=2,mode=nearest,transpose=0): not supported [BLAS] 
116s   UPSCALE(type=f32,ne=[512,512,3,2],scale_factor=2,mode=nearest,transpose=1): not supported [BLAS] 
116s   UPSCALE(type=f32,ne=[2,5,7,11],ne_tgt=[5,7,11,13],mode=0): not supported [BLAS] 
116s   UPSCALE(type=f32,ne=[5,7,11,13],ne_tgt=[2,5,7,11],mode=0): not supported [BLAS] 
116s   UPSCALE(type=f32,ne=[512,512,3,2],scale_factor=2,mode=bilinear,transpose=0): not supported [BLAS] 
116s   UPSCALE(type=f32,ne=[512,512,3,2],scale_factor=2,mode=bilinear,transpose=1): not supported [BLAS] 
116s   UPSCALE(type=f32,ne=[2,5,7,11],ne_tgt=[5,7,11,13],mode=1): not supported [BLAS] 
116s   UPSCALE(type=f32,ne=[5,7,11,13],ne_tgt=[2,5,7,11],mode=1): not supported [BLAS] 
116s   UPSCALE(type=f32,ne=[2,5,7,11],ne_tgt=[5,7,11,13],mode=257): not supported [BLAS] 
116s   SUM(type=f32,ne=[10,5,4,3]): not supported [BLAS] 
116s   SUM_ROWS(type=f32,ne=[10,5,4,3],permute=0,slice=0): not supported [BLAS] 
116s   SUM_ROWS(type=f32,ne=[11,5,6,3],permute=1,slice=0): not supported [BLAS] 
116s   SUM_ROWS(type=f32,ne=[11,5,6,3],permute=0,slice=1): not supported [BLAS] 
116s   SUM_ROWS(type=f32,ne=[11,5,6,3],permute=1,slice=1): not supported [BLAS] 
116s   MEAN(type=f32,ne=[10,5,4,3]): not supported [BLAS] 
116s   SUM(type=f32,ne=[33,1,1,1]): not supported [BLAS] 
116s   SUM_ROWS(type=f32,ne=[33,1,1,1],permute=0,slice=0): not supported [BLAS] 
116s   MEAN(type=f32,ne=[33,1,1,1]): not supported [BLAS] 
116s   SUM(type=f32,ne=[33,1024,1,1]): not supported [BLAS] 
116s   SUM_ROWS(type=f32,ne=[33,1024,1,1],permute=0,slice=0): not supported [BLAS] 
116s   SUM(type=f32,ne=[33,256,1,1]): not supported [BLAS] 
116s   SUM_ROWS(type=f32,ne=[33,256,1,1],permute=0,slice=0): not supported [BLAS] 
116s   MEAN(type=f32,ne=[33,256,1,1]): not supported [BLAS] 
116s   MEAN(type=f32,ne=[32769,1,1,1]): not supported [BLAS] 
116s   GROUP_NORM(type=f32,ne=[64,64,320,1],num_groups=32,eps=0.000001): not supported [BLAS] 
116s   GROUP_NORM(type=f32,ne=[9,9,1280,1],num_groups=32,eps=0.000001): not supported [BLAS] 
116s   GROUP_NORM_MUL_ADD(type=f32,ne=[64,64,320,1],num_groups=4,eps=0.000010): not supported [BLAS] 
116s   GROUP_NORM_MUL_ADD(type=f32,ne=[9,9,1280,1],num_groups=4,eps=0.000010): not supported [BLAS] 
116s   ACC(type=f32,ne_a=[256,17,1,1],ne_b=[256,16,1,1]): not supported [BLAS] 
116s   PAD(type=f32,ne_a=[512,512,1,1],pad_0=1,pad_1=1): not supported [BLAS] 
116s   PAD(type=f32,ne_a=[512,512,3,1],lp0=1,rp0=1,lp1=1,rp1=1,lp2=1,rp2=1,lp3=1,rp3=1,v=0): not supported [BLAS] 
116s   PAD_REFLECT_1D(type=f32,ne_a=[512,34,2,1],pad_0=10,pad_1=9): not supported [BLAS] 
116s   PAD_REFLECT_1D(type=f32,ne_a=[3000,384,4,1],pad_0=10,pad_1=9): not supported [BLAS] 
116s   ROLL(shift0=3,shift1=-2,shift3=1,shift4=-1): not supported [BLAS] 
116s   ARANGE(type=f32,start=0.000000,stop=10.000000,step=1.000000): not supported [BLAS] 
116s   TIMESTEP_EMBEDDING(type=f32,ne_a=[2,1,1,1],dim=320,max_period=10000): not supported [BLAS] 
116s   LEAKY_RELU(type=f32,ne_a=[10,5,4,3],negative_slope=0.100000): not supported [BLAS] 
116s   PAD(type=f32,ne_a=[512,512,1,1],lp0=0,rp0=1,lp1=0,rp1=1,lp2=0,rp2=0,lp3=0,rp3=0,v=0): not supported [BLAS] 
116s   PAD(type=f32,ne_a=[11,22,33,44],lp0=1,rp0=2,lp1=3,rp1=4,lp2=5,rp2=6,lp3=7,rp3=8,v=0): not supported [BLAS] 
116s   PAD(type=f32,ne_a=[512,512,1,1],lp0=0,rp0=1,lp1=0,rp1=1,lp2=0,rp2=0,lp3=0,rp3=0,v=1): not supported [BLAS] 
116s   PAD(type=f32,ne_a=[11,22,33,44],lp0=1,rp0=2,lp1=3,rp1=4,lp2=5,rp2=6,lp3=7,rp3=8,v=1): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=40,hsv=40,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=80,hsv=80,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=96,hsv=96,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=128,hsv=128,nh=4,nr23=[16,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=10.000000,prec=def,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=128,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=192,hsv=192,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=256,hsv=256,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,2,1,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[1,1],kv=1024,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q8_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   FLASH_ATTN_EXT(hsk=576,hsv=512,nh=4,nr23=[4,1],kv=512,nb=35,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=q4_0,permute=[0,1,2,3]): not supported [BLAS] 
116s   CROSS_ENTROPY_LOSS(type=f32,ne=[10,5,4,3]): not supported [BLAS] 
116s   CROSS_ENTROPY_LOSS(type=f32,ne=[30000,1,1,1]): not supported [BLAS] 
116s   CROSS_ENTROPY_LOSS_BACK(type=f32,ne=[10,5,4,3]): not supported [BLAS] 
116s   CROSS_ENTROPY_LOSS_BACK(type=f32,ne=[30000,1,1,1]): not supported [BLAS] 
116s   OPT_STEP_ADAMW(type=f32,ne=[10,5,4,3]): not supported [BLAS] 
116s   OPT_STEP_SGD(type=f32,ne=[10,5,4,3]): not supported [BLAS] 
116s   TOPK_MOE(ne=[8,22,1,1],n_expert_used=4,with_norm=0): not supported [BLAS] 
116s   TOPK_MOE(ne=[32,22,1,1],n_expert_used=8,with_norm=0): not supported [BLAS] 
116s   TOPK_MOE(ne=[128,1,1,1],n_expert_used=128,with_norm=0): not supported [BLAS] 
116s   TOPK_MOE(ne=[8,22,1,1],n_expert_used=4,with_norm=1): not supported [BLAS] 
116s   TOPK_MOE(ne=[32,22,1,1],n_expert_used=8,with_norm=1): not supported [BLAS] 
116s   TOPK_MOE(ne=[128,1,1,1],n_expert_used=128,with_norm=1): not supported [BLAS] 
116s   14598/14598 tests passed
116s   Backend BLAS: OK
116s Backend 2/2: CPU
116s   Skipping CPU backend
116s 2/2 backends passed
116s OK
117s autopkgtest [23:57:30]: test libggml0-backend-blas: -----------------------]
117s libggml0-backend-blas PASS
117s autopkgtest [23:57:30]: test libggml0-backend-blas:  - - - - - - - - - - results - - - - - - - - - -
118s autopkgtest [23:57:31]: test libggml0-backend-hip: preparing testbed
124s Creating nova instance adt-resolute-amd64-ggml-20251031-235533-juju-7f2275-prod-proposed-migration-environment-20-a2e36e32-01db-4661-a4d2-47c12274a09b from image adt/ubuntu-resolute-amd64-server-20251031.img (UUID eaf9d537-af66-471e-af1e-6f7da9a9a444)...
155s autopkgtest [23:58:08]: testbed dpkg architecture: amd64
155s autopkgtest [23:58:08]: testbed apt version: 3.1.11
156s autopkgtest [23:58:09]: @@@@@@@@@@@@@@@@@@@@ test bed setup
156s autopkgtest [23:58:09]: testbed release detected to be: resolute
156s autopkgtest [23:58:09]: updating testbed package index (apt update)
157s Get:1 http://ftpmaster.internal/ubuntu resolute-proposed InRelease [87.8 kB]
157s Hit:2 http://ftpmaster.internal/ubuntu resolute InRelease
157s Hit:3 http://ftpmaster.internal/ubuntu resolute-updates InRelease
157s Hit:4 http://ftpmaster.internal/ubuntu resolute-security InRelease
157s Get:5 http://ftpmaster.internal/ubuntu resolute-proposed/restricted Sources [9848 B]
157s Get:6 http://ftpmaster.internal/ubuntu resolute-proposed/multiverse Sources [50.7 kB]
157s Get:7 http://ftpmaster.internal/ubuntu resolute-proposed/main Sources [155 kB]
157s Get:8 http://ftpmaster.internal/ubuntu resolute-proposed/universe Sources [2759 kB]
157s Get:9 http://ftpmaster.internal/ubuntu resolute-proposed/main i386 Packages [160 kB]
157s Get:10 http://ftpmaster.internal/ubuntu resolute-proposed/main amd64 Packages [244 kB]
157s Get:11 http://ftpmaster.internal/ubuntu resolute-proposed/main amd64 c-n-f Metadata [5004 B]
157s Get:12 http://ftpmaster.internal/ubuntu resolute-proposed/restricted amd64 Packages [64.6 kB]
157s Get:13 http://ftpmaster.internal/ubuntu resolute-proposed/restricted i386 Packages [3744 B]
157s Get:14 http://ftpmaster.internal/ubuntu resolute-proposed/restricted amd64 c-n-f Metadata [336 B]
157s Get:15 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 Packages [1995 kB]
158s Get:16 http://ftpmaster.internal/ubuntu resolute-proposed/universe i386 Packages [836 kB]
158s Get:17 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 c-n-f Metadata [52.7 kB]
158s Get:18 http://ftpmaster.internal/ubuntu resolute-proposed/multiverse amd64 Packages [38.8 kB]
158s Get:19 http://ftpmaster.internal/ubuntu resolute-proposed/multiverse i386 Packages [14.7 kB]
158s Get:20 http://ftpmaster.internal/ubuntu resolute-proposed/multiverse amd64 c-n-f Metadata [1916 B]
158s Fetched 6478 kB in 1s (6018 kB/s)
159s Reading package lists...
159s Hit:1 http://ftpmaster.internal/ubuntu resolute-proposed InRelease
159s Hit:2 http://ftpmaster.internal/ubuntu resolute InRelease
159s Hit:3 http://ftpmaster.internal/ubuntu resolute-updates InRelease
159s Hit:4 http://ftpmaster.internal/ubuntu resolute-security InRelease
160s Reading package lists...
160s Reading package lists...
160s Building dependency tree...
160s Reading state information...
160s Calculating upgrade...
160s The following packages will be upgraded:
160s   libfribidi0
160s 1 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
160s Need to get 26.5 kB of archives.
160s After this operation, 0 B of additional disk space will be used.
160s Get:1 http://ftpmaster.internal/ubuntu resolute/main amd64 libfribidi0 amd64 1.0.16-3 [26.5 kB]
160s dpkg-preconfigure: unable to re-open stdin: No such file or directory
160s Fetched 26.5 kB in 0s (1280 kB/s)
161s (Reading database ... 
(Reading database ... 5%
(Reading database ... 10%
(Reading database ... 15%
(Reading database ... 20%
(Reading database ... 25%
(Reading database ... 30%
(Reading database ... 35%
(Reading database ... 40%
(Reading database ... 45%
(Reading database ... 50%
(Reading database ... 55%
(Reading database ... 60%
(Reading database ... 65%
(Reading database ... 70%
(Reading database ... 75%
(Reading database ... 80%
(Reading database ... 85%
(Reading database ... 90%
(Reading database ... 95%
(Reading database ... 100%
(Reading database ... 78534 files and directories currently installed.)
161s Preparing to unpack .../libfribidi0_1.0.16-3_amd64.deb ...
161s Unpacking libfribidi0:amd64 (1.0.16-3) over (1.0.16-1) ...
161s Setting up libfribidi0:amd64 (1.0.16-3) ...
161s Processing triggers for libc-bin (2.42-0ubuntu3) ...
161s autopkgtest [23:58:14]: upgrading testbed (apt dist-upgrade and autopurge)
161s Reading package lists...
161s Building dependency tree...
161s Reading state information...
161s Calculating upgrade...
161s 0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
161s Reading package lists...
161s Building dependency tree...
161s Reading state information...
162s Solving dependencies...
162s 0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
164s Reading package lists...
164s Building dependency tree...
164s Reading state information...
164s Solving dependencies...
164s The following NEW packages will be installed:
164s   libamd-comgr2 libamd-comgr3 libamdhip64-5 libamdhip64-6 libdrm-amdgpu1
164s   libfmt10 libggml0 libggml0-backend-cpu libggml0-backend-hip libgomp1
164s   libhipblas0 libhsa-runtime64-1 libhsakmt1 libllvm17t64 libllvm21 librocblas0
164s   librocsolver0 pkg-rocm-tools
164s 0 upgraded, 18 newly installed, 0 to remove and 0 not upgraded.
164s Need to get 836 MB of archives.
164s After this operation, 4980 MB of additional disk space will be used.
164s Get:1 http://ftpmaster.internal/ubuntu resolute/universe amd64 libllvm17t64 amd64 1:17.0.6-22build1 [25.9 MB]
165s Get:2 http://ftpmaster.internal/ubuntu resolute/universe amd64 libamd-comgr2 amd64 6.0+git20231212.4510c28+dfsg-3build3 [14.3 MB]
165s Get:3 http://ftpmaster.internal/ubuntu resolute/main amd64 libllvm21 amd64 1:21.1.2-2ubuntu6 [30.7 MB]
166s Get:4 http://ftpmaster.internal/ubuntu resolute/universe amd64 libamd-comgr3 amd64 7.0.2+dfsg-1 [15.2 MB]
166s Get:5 http://ftpmaster.internal/ubuntu resolute/main amd64 libdrm-amdgpu1 amd64 2.4.127-1ubuntu1 [23.6 kB]
166s Get:6 http://ftpmaster.internal/ubuntu resolute/universe amd64 libhsakmt1 amd64 6.4.3+dfsg-3 [67.5 kB]
166s Get:7 http://ftpmaster.internal/ubuntu resolute/universe amd64 libhsa-runtime64-1 amd64 6.4.3+dfsg-3 [630 kB]
166s Get:8 http://ftpmaster.internal/ubuntu resolute/universe amd64 libamdhip64-5 amd64 5.7.1-6 [9698 kB]
167s Get:9 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 libamdhip64-6 amd64 6.4.3-3 [10.3 MB]
167s Get:10 http://ftpmaster.internal/ubuntu resolute/universe amd64 libfmt10 amd64 10.1.1+ds1-4 [79.0 kB]
167s Get:11 http://ftpmaster.internal/ubuntu resolute/main amd64 libgomp1 amd64 15.2.0-5ubuntu1 [151 kB]
167s Get:12 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 libggml0-backend-cpu amd64 0.9.4-3 [711 kB]
167s Get:13 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 libggml0 amd64 0.9.4-3 [373 kB]
167s Get:14 http://ftpmaster.internal/ubuntu resolute/universe amd64 librocblas0 amd64 5.5.1+dfsg-7 [178 MB]
172s Get:15 http://ftpmaster.internal/ubuntu resolute/universe amd64 librocsolver0 amd64 5.5.1-7 [479 MB]
185s Get:16 http://ftpmaster.internal/ubuntu resolute/universe amd64 libhipblas0 amd64 5.5.1-4build1 [81.6 kB]
185s Get:17 http://ftpmaster.internal/ubuntu resolute-proposed/universe amd64 libggml0-backend-hip amd64 0.9.4-3 [70.6 MB]
187s Get:18 http://ftpmaster.internal/ubuntu resolute/universe amd64 pkg-rocm-tools all 0.8.2 [7130 B]
188s Fetched 836 MB in 23s (36.0 MB/s)
188s Selecting previously unselected package libllvm17t64:amd64.
188s (Reading database ... 
(Reading database ... 5%
(Reading database ... 10%
(Reading database ... 15%
(Reading database ... 20%
(Reading database ... 25%
(Reading database ... 30%
(Reading database ... 35%
(Reading database ... 40%
(Reading database ... 45%
(Reading database ... 50%
(Reading database ... 55%
(Reading database ... 60%
(Reading database ... 65%
(Reading database ... 70%
(Reading database ... 75%
(Reading database ... 80%
(Reading database ... 85%
(Reading database ... 90%
(Reading database ... 95%
(Reading database ... 100%
(Reading database ... 78534 files and directories currently installed.)
188s Preparing to unpack .../00-libllvm17t64_1%3a17.0.6-22build1_amd64.deb ...
188s Unpacking libllvm17t64:amd64 (1:17.0.6-22build1) ...
188s Selecting previously unselected package libamd-comgr2:amd64.
188s Preparing to unpack .../01-libamd-comgr2_6.0+git20231212.4510c28+dfsg-3build3_amd64.deb ...
188s Unpacking libamd-comgr2:amd64 (6.0+git20231212.4510c28+dfsg-3build3) ...
188s Selecting previously unselected package libllvm21:amd64.
188s Preparing to unpack .../02-libllvm21_1%3a21.1.2-2ubuntu6_amd64.deb ...
188s Unpacking libllvm21:amd64 (1:21.1.2-2ubuntu6) ...
188s Selecting previously unselected package libamd-comgr3:amd64.
188s Preparing to unpack .../03-libamd-comgr3_7.0.2+dfsg-1_amd64.deb ...
188s Unpacking libamd-comgr3:amd64 (7.0.2+dfsg-1) ...
189s Selecting previously unselected package libdrm-amdgpu1:amd64.
189s Preparing to unpack .../04-libdrm-amdgpu1_2.4.127-1ubuntu1_amd64.deb ...
189s Unpacking libdrm-amdgpu1:amd64 (2.4.127-1ubuntu1) ...
189s Selecting previously unselected package libhsakmt1:amd64.
189s Preparing to unpack .../05-libhsakmt1_6.4.3+dfsg-3_amd64.deb ...
189s Unpacking libhsakmt1:amd64 (6.4.3+dfsg-3) ...
189s Selecting previously unselected package libhsa-runtime64-1:amd64.
189s Preparing to unpack .../06-libhsa-runtime64-1_6.4.3+dfsg-3_amd64.deb ...
189s Unpacking libhsa-runtime64-1:amd64 (6.4.3+dfsg-3) ...
189s Selecting previously unselected package libamdhip64-5:amd64.
189s Preparing to unpack .../07-libamdhip64-5_5.7.1-6_amd64.deb ...
189s Unpacking libamdhip64-5:amd64 (5.7.1-6) ...
189s Selecting previously unselected package libamdhip64-6:amd64.
189s Preparing to unpack .../08-libamdhip64-6_6.4.3-3_amd64.deb ...
189s Unpacking libamdhip64-6:amd64 (6.4.3-3) ...
189s Selecting previously unselected package libfmt10:amd64.
189s Preparing to unpack .../09-libfmt10_10.1.1+ds1-4_amd64.deb ...
189s Unpacking libfmt10:amd64 (10.1.1+ds1-4) ...
189s Selecting previously unselected package libgomp1:amd64.
189s Preparing to unpack .../10-libgomp1_15.2.0-5ubuntu1_amd64.deb ...
189s Unpacking libgomp1:amd64 (15.2.0-5ubuntu1) ...
189s Selecting previously unselected package libggml0-backend-cpu:amd64.
189s Preparing to unpack .../11-libggml0-backend-cpu_0.9.4-3_amd64.deb ...
189s Unpacking libggml0-backend-cpu:amd64 (0.9.4-3) ...
189s Selecting previously unselected package libggml0:amd64.
189s Preparing to unpack .../12-libggml0_0.9.4-3_amd64.deb ...
189s Unpacking libggml0:amd64 (0.9.4-3) ...
189s Selecting previously unselected package librocblas0.
189s Preparing to unpack .../13-librocblas0_5.5.1+dfsg-7_amd64.deb ...
189s Unpacking librocblas0 (5.5.1+dfsg-7) ...
193s Selecting previously unselected package librocsolver0.
193s Preparing to unpack .../14-librocsolver0_5.5.1-7_amd64.deb ...
193s Unpacking librocsolver0 (5.5.1-7) ...
197s Selecting previously unselected package libhipblas0.
197s Preparing to unpack .../15-libhipblas0_5.5.1-4build1_amd64.deb ...
197s Unpacking libhipblas0 (5.5.1-4build1) ...
197s Selecting previously unselected package libggml0-backend-hip:amd64.
197s Preparing to unpack .../16-libggml0-backend-hip_0.9.4-3_amd64.deb ...
197s Unpacking libggml0-backend-hip:amd64 (0.9.4-3) ...
198s Selecting previously unselected package pkg-rocm-tools.
198s Preparing to unpack .../17-pkg-rocm-tools_0.8.2_all.deb ...
198s Unpacking pkg-rocm-tools (0.8.2) ...
198s Setting up libgomp1:amd64 (15.2.0-5ubuntu1) ...
198s Setting up libllvm17t64:amd64 (1:17.0.6-22build1) ...
198s Setting up libllvm21:amd64 (1:21.1.2-2ubuntu6) ...
198s Setting up libamd-comgr3:amd64 (7.0.2+dfsg-1) ...
198s Setting up libamd-comgr2:amd64 (6.0+git20231212.4510c28+dfsg-3build3) ...
198s Setting up pkg-rocm-tools (0.8.2) ...
198s Setting up libfmt10:amd64 (10.1.1+ds1-4) ...
198s Setting up libdrm-amdgpu1:amd64 (2.4.127-1ubuntu1) ...
198s Setting up libhsakmt1:amd64 (6.4.3+dfsg-3) ...
198s Setting up libhsa-runtime64-1:amd64 (6.4.3+dfsg-3) ...
198s Setting up libamdhip64-5:amd64 (5.7.1-6) ...
198s Setting up libamdhip64-6:amd64 (6.4.3-3) ...
198s Setting up librocblas0 (5.5.1+dfsg-7) ...
198s Setting up librocsolver0 (5.5.1-7) ...
198s Setting up libhipblas0 (5.5.1-4build1) ...
198s Setting up libggml0-backend-cpu:amd64 (0.9.4-3) ...
198s Setting up libggml0:amd64 (0.9.4-3) ...
198s Setting up libggml0-backend-hip:amd64 (0.9.4-3) ...
198s Processing triggers for libc-bin (2.42-0ubuntu3) ...
198s Processing triggers for man-db (2.13.1-1) ...
201s autopkgtest [23:58:54]: test libggml0-backend-hip: rocm-test-launcher /usr/libexec/ggml/runtests
201s autopkgtest [23:58:54]: test libggml0-backend-hip: [-----------------------
201s /dev/kfd not present, system either lacks AMD GPU or 'amdgpu' driver is not loaded.
201s Skipping tests.
201s autopkgtest [23:58:54]: test libggml0-backend-hip: -----------------------]
201s autopkgtest [23:58:54]: test libggml0-backend-hip:  - - - - - - - - - - results - - - - - - - - - -
201s libggml0-backend-hip SKIP exit status 77 and marked as skippable
202s autopkgtest [23:58:55]: @@@@@@@@@@@@@@@@@@@@ summary
202s libggml0-backend-cpu PASS
202s libggml0-backend-blas PASS
202s libggml0-backend-hip SKIP exit status 77 and marked as skippable