ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 18:17:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit 'bab747b017f3f2102d59f15f08953055d5edc0f4' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-09-02 16:12:59 +00:00
parent 754d2fcb68
commit 12e20f7a0b
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
profiler/include/profiler/profile_gemm_blockscale_wp_impl.hpp
View File

@@ -107,7 +107,7 @@ bool profile_gemm_blockscale_weighpreshuffle_impl(int do_verification,
ck::utils::validate_gemm_stride<ALayout>(M, K, StrideA, "StrideA");
ck::utils::validate_gemm_stride<BLayout>(K, N, StrideB, "StrideB");
ck::utils::validate_gemm_stride<BLayout>(M, N, StrideE, "StrideE");
ck::utils::validate_gemm_stride<ELayout>(M, N, StrideE, "StrideE");
Tensor<A0DataType> a0_m_k(f_host_tensor_descriptor(M, K, StrideA, ALayout{}));
Tensor<A1DataType> a1_m_k(f_host_tensor_descriptor((M + ScaleBlockM - 1) / ScaleBlockM,