Skip to content

test-backend-ops : add option -p to filter by op params #12155

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 1 commit into from
Mar 3, 2025
Merged

test-backend-ops : add option -p to filter by op params #12155

merged 1 commit into from
Mar 3, 2025

Conversation

@slaren
Copy link
Member

@slaren slaren commented Mar 2, 2025 •
edited
Loading

Filters test cases by its params string, using a regex.

Mainly I expect this to be useful with perf to be able to run only the tests that you care about without having to modify the code. For example, you can use test-backend-ops -o MUL_MAT -p "type_a=q4_0.*n=(1|512)" perf to run only MUL_MAT cases with type_a=q4_0 and n=1|512.

@github-actions github-actions bot added the testing Everything test related label Mar 2, 2025
@jeffzhou2000
Copy link

jeffzhou2000 commented Mar 3, 2025 •
edited
Loading

this feature is very helpful for backend developers and it will make workflow more simple and easy, it might be more helpful to add some additional params in the "params regex", e.g.:

test-backend-ops -o MUL_MAT -p "type_a=q4_0.type_b=fp32.axb=[512,512]x[512,512]"

test-backend-ops -b xxx-gpu -o MUL_MAT -p "type_a=q4_0.type_b=fp32.axb=[256,16,3,2]x[256,1,6,4]"

this feature will really helps backend developers a lot. hope it can be seen in the master branch soon then backend developers can modify codes/scripts accordingly. thanks too much!

@slaren slaren merged commit d5c63cd into master Mar 3, 2025
43 of 47 checks passed
@slaren slaren deleted the sl/tbops-params-filter branch March 3, 2025 13:00
@jeffzhou2000
Copy link

jeffzhou2000 commented Mar 4, 2025 •
edited
Loading

thanks for this very helpful feature can be seen in the master branch, I already updated my local dev branch accordingly:
jeffzhou2000@5a789d8

this feature seems simple but works very effective and very helpful for backend developers, thanks again!

zhouwg:$ ./scripts/build-run-android.sh
current working path:/home/zhouwg/kantvai/llama.cpp

Usage:
  ./scripts/build-run-android.sh help
  ./scripts/build-run-android.sh print_oplist
  ./scripts/build-run-android.sh build
  ./scripts/build-run-android.sh updateqnnlib
  ./scripts/build-run-android.sh run_testops
  ./scripts/build-run-android.sh run_testop          [ADD/MUL/MUL_MAT]  [0 (QNN_CPU) / 1 (QNN_GPU) / 2 (QNN_NPU)]
  ./scripts/build-run-android.sh run_ut_add          0 (QNN_CPU) / 1 (QNN_GPU) / 2 (QNN_NPU) / 3 (ggml)
  ./scripts/build-run-android.sh run_ut_mulmat       0 (QNN_CPU) / 1 (QNN_GPU) / 2 (QNN_NPU) / 3 (ggml)
  ./scripts/build-run-android.sh run_ut_mul          0 (QNN_CPU) / 1 (QNN_GPU) / 2 (QNN_NPU) / 3 (ggml)
  ./scripts/build-run-android.sh run_llamacli        0 (QNN_CPU) / 1 (QNN_GPU) / 2 (QNN_NPU) / 3 (ggml)
  ./scripts/build-run-android.sh run_llamabench      0 (QNN_CPU) / 1 (QNN_GPU) / 2 (QNN_NPU) / 3 (ggml)


zhouwg:$ ./scripts/build-run-android.sh print_oplist
current working path:/home/zhouwg/kantvai/llama.cpp

opname list: 
DUP ADD ADD1 ACC SUB MUL DIV SQR SQRT LOG SIN COS SUM SUM_ROWS MEAN ARGMAX COUNT_EQUAL REPEAT REPEAT_BACK CONCAT SILU_BACK NORM RMS_NORM RMS_NORM_BACK GROUP_NORM MUL_MAT MUL_MAT_ID OUT_PROD SCALE SET CPY CONT RESHAPE VIEW PERMUTE TRANSPOSE GET_ROWS GET_ROWS_BACK DIAG DIAG_MASK_INF DIAG_MASK_ZERO SOFT_MAX SOFT_MAX_BACK ROPE ROPE_BACK CLAMP CONV_TRANSPOSE_1D IM2COL IM2COL_BACK CONV_TRANSPOSE_2D POOL_1D POOL_2D POOL_2D_BACK UPSCALE PAD PAD_REFLECT_1D ARANGE TIMESTEP_EMBEDDING ARGSORT LEAKY_RELU FLASH_ATTN_EXT FLASH_ATTN_BACK SSM_CONV SSM_SCAN WIN_PART WIN_UNPART GET_REL_POS ADD_REL_POS RWKV_WKV6 GATED_LINEAR_ATTN


zhouwg:$ ./scripts/build-run-android.sh run_testop MUL_MAT 2
current working path:/home/zhouwg/kantvai/llama.cpp

/data/local/tmp//libQnnCpu.so
QNN libs already exist on Android phone
./out/android/bin/libggml-base.so: 1 file pushed. 17.5 MB/s (4630256 bytes in 0.252s)
./out/android/bin/libggml-cpu.so: 1 file pushed. 17.0 MB/s (2299384 bytes in 0.129s)
./out/android/bin/libggml-qnn.so: 1 file pushed. 16.7 MB/s (1570312 bytes in 0.089s)
./out/android/bin/libggml.so: 1 file pushed. 17.2 MB/s (561320 bytes in 0.031s)
./out/android/bin/libllama.so: 1 file pushed. 20.2 MB/s (16467208 bytes in 0.778s)
./out/android/bin/libllava_shared.so: 1 file pushed. 17.5 MB/s (3138864 bytes in 0.171s)
6 files pushed. 18.8 MB/s (28667344 bytes in 1.454s)
./out/android/bin/test-backend-ops: 1 file pushed. 17.6 MB/s (4443448 bytes in 0.241s)
adb shell cd /data/local/tmp/                && export LD_LIBRARY_PATH=/data/local/tmp/                && /data/local/tmp//test-backend-ops test -o MUL_MAT -b qnn-npu 
\n
Testing 4 devices

Backend 1/4: qnn-cpu
  Skipping
Backend 2/4: qnn-gpu
  Skipping
Backend 3/4: qnn-npu
[ggml_backend_qnn_init, 2917]: QNN NPU backend setenv successfully
[ggml_backend_qnn_init, 2925]: QNN NPU backend setenv successfully
[load_system, 1593]: find a valid qnn system interface

[load_system, 1603]: initialize qnn system successfully

[load_backend, 1472]: find a valid qnn interface

[qnn_init, 1755]: create device successfully

[qnn_init, 1759]: profiling turned on; level = 2
[qnn_init, 1770]: detailed profiling requested. Creating Qnn Profile object

[qnn_init, 1824]: device counts 1
[qnn_init, 1828]: deviceID:0, deviceType:0, numCores 1
[qnn_init, 1833]: htp_type:0(QNN_HTP_DEVICE_TYPE_ON_CHIP)
[qnn_init, 1836]: qualcomm soc_model:57(SM8650), htp_arch:75(QCOM_HTP_V75), vtcm_size:8 MB
[qnn_init, 1841]: soc info:Qualcomm SnapDragon 8 Gen 3 
[probe_device_meminfo, 2144]: capacity of rpc ion memory 2000 MB

[ggml_backend_qnn_init, 2957]: qnn device name QNN-NPU
  Device description: Qualcomm NPU(Hexagon Tensor Processor)SM8650_QCOM_HTP_V75,Qualcomm SnapDragon 8 Gen 3 
  Device memory: 2000 MB (2000 MB free)

  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]): not supported [qnn-npu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): OK
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): OK
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): OK
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): OK
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): OK
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] not supported [CPU] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  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]): not supported [qnn-npu] 
  4109/4109 tests passed
  Backend qnn-npu: OK

Backend 4/4: CPU
  Skipping
4/4 backends passed
OK

zhouwg:$ ./scripts/build-run-android.sh run_testop MUL_MAT 0
current working path:/home/zhouwg/kantvai/llama.cpp

/data/local/tmp//libQnnCpu.so
QNN libs already exist on Android phone
./out/android/bin/libggml-base.so: 1 file pushed. 17.5 MB/s (4630256 bytes in 0.252s)
./out/android/bin/libggml-cpu.so: 1 file pushed. 17.3 MB/s (2299384 bytes in 0.127s)
./out/android/bin/libggml-qnn.so: 1 file pushed. 16.7 MB/s (1570312 bytes in 0.090s)
./out/android/bin/libggml.so: 1 file pushed. 15.8 MB/s (561320 bytes in 0.034s)
./out/android/bin/libllama.so: 1 file pushed. 17.4 MB/s (16467208 bytes in 0.904s)
./out/android/bin/libllava_shared.so: 1 file pushed. 16.8 MB/s (3138864 bytes in 0.178s)
6 files pushed. 17.2 MB/s (28667344 bytes in 1.588s)
./out/android/bin/test-backend-ops: 1 file pushed. 17.4 MB/s (4443448 bytes in 0.244s)
adb shell cd /data/local/tmp/                && export LD_LIBRARY_PATH=/data/local/tmp/                && /data/local/tmp//test-backend-ops test -o MUL_MAT -b qnn-cpu 
\n
Testing 4 devices

Backend 1/4: qnn-cpu
[ggml_backend_qnn_init, 2934]: QNN-CPU backend setenv successfully

[load_system, 1593]: find a valid qnn system interface

[load_system, 1603]: initialize qnn system successfully

[load_backend, 1472]: find a valid qnn interface

[qnn_init, 1755]: create device successfully

[qnn_init, 1759]: profiling turned on; level = 2
[qnn_init, 1770]: detailed profiling requested. Creating Qnn Profile object

[ggml_backend_qnn_init, 2957]: qnn device name QNN-CPU
  Device description: Qualcomm Kryo CPU
  Device memory: 19397 MB (5544 MB free)

  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): OK
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] not supported [CPU] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  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]): not supported [qnn-cpu] 
  4109/4109 tests passed
  Backend qnn-cpu: OK

Backend 2/4: qnn-gpu
  Skipping
Backend 3/4: qnn-npu
  Skipping
Backend 4/4: CPU
  Skipping
4/4 backends passed
OK

mglambda pushed a commit to mglambda/llama.cpp that referenced this pull request Mar 8, 2025
@slaren @mglambda
test-backend-ops : add option -p to filter by op params (ggml-org#12155)
6a3f171
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Mar 19, 2025
@slaren @arthw
test-backend-ops : add option -p to filter by op params (ggml-org#12155)
3049c9e
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@ggerganov ggerganov ggerganov approved these changes

Assignees

No one assigned

Labels

testing Everything test related

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@slaren @jeffzhou2000 @ggerganov