Skip to content
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

move changes for avx512 blklen32 special layout from liqun/avx-layout #23331

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from

move changes for avx512 blklen32 special layout from liqun/avx-layout

ab3bff7
Select commit
Loading
Failed to load commit list.
Draft

move changes for avx512 blklen32 special layout from liqun/avx-layout #23331

move changes for avx512 blklen32 special layout from liqun/avx-layout
ab3bff7
Select commit
Loading
Failed to load commit list.
Azure Pipelines / Windows GPU DML CI Pipeline failed Jan 11, 2025 in 29m 0s

Build #20250111.2 failed

6 errors / 84 warnings

Annotations

Check failure on line 177 in onnxruntime\core\mlas\lib\sqnbitgemm_kernel_avx512.cpp

See this annotation in the file changed.

@azure-pipelines azure-pipelines / Windows GPU DML CI Pipeline

onnxruntime\core\mlas\lib\sqnbitgemm_kernel_avx512.cpp#L177 

onnxruntime\core\mlas\lib\sqnbitgemm_kernel_avx512.cpp(177,9): Error C2672: 'MlasQ4Int8GemmKernelBlkLen16Avx512': no matching overloaded function found

Check failure on line 207 in onnxruntime\core\mlas\lib\sqnbitgemm_kernel_avx512.cpp

See this annotation in the file changed.

@azure-pipelines azure-pipelines / Windows GPU DML CI Pipeline

onnxruntime\core\mlas\lib\sqnbitgemm_kernel_avx512.cpp#L207 

onnxruntime\core\mlas\lib\sqnbitgemm_kernel_avx512.cpp(207,9): Error C2672: 'MlasQ4Int8GemmKernelBlkLen64Avx512': no matching overloaded function found

Check failure on line 223 in onnxruntime\core\mlas\lib\sqnbitgemm_kernel_avx512.cpp

See this annotation in the file changed.

@azure-pipelines azure-pipelines / Windows GPU DML CI Pipeline

onnxruntime\core\mlas\lib\sqnbitgemm_kernel_avx512.cpp#L223 

onnxruntime\core\mlas\lib\sqnbitgemm_kernel_avx512.cpp(223,9): Error C2672: 'MlasQ4Int8GemmKernelBlkLen128Avx512': no matching overloaded function found

Check failure on line 533 in onnxruntime\core\mlas\lib\sqnbitgemm_kernel_avx512.cpp

See this annotation in the file changed.

@azure-pipelines azure-pipelines / Windows GPU DML CI Pipeline

onnxruntime\core\mlas\lib\sqnbitgemm_kernel_avx512.cpp#L533 

onnxruntime\core\mlas\lib\sqnbitgemm_kernel_avx512.cpp(533,42): Error C2440: '=': cannot convert from 'size_t (__cdecl *)(const size_t,const std::byte *,const float *,const std::byte *,const float *,float *,size_t,size_t,size_t,size_t,const float *,size_t,const float *,const float *)' to 'MLAS_QNBIT_GEMM_DISPATCH::SQ4BitGemmKernel_BlkSum_CompInt8_Fn (__cdecl *)'
View more details on Azure Pipelines