ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-07-12 02:05:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updates to support mixed precision

Browse Source 
(cherry picked from commit e65d71180393e7b66169c56565a6bac740427de6)

Co-authored-by: Anca Hamuraru <anca@streamhpc.com>
This commit is contained in:
Anca Hamuraru
2025-05-01 12:51:21 +00:00
parent 12176616b6
commit df929f094a
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_wmmaops_base.hpp
View File

@@ -282,7 +282,7 @@ struct BlockwiseGemmWmmaops_pipeline_base
using AThreadCopy =
ThreadwiseTensorSliceTransfer_v4<ADataType,
ADataType,
ComputeTypeA,
decltype(a_block_desc_k0_m0_m1_m2_k1),
decltype(a_thread_desc_),
Sequence<KPack / A_K1 / A_KRow, 1, 1, 1, 1, A_K1>,
@@ -293,7 +293,7 @@ struct BlockwiseGemmWmmaops_pipeline_base
using BThreadCopy =
ThreadwiseTensorSliceTransfer_v4<BDataType,
BDataType,
ComputeTypeB,
decltype(b_block_desc_k0_n0_n1_n2_k1),
decltype(b_thread_desc_),
Sequence<KPack / B_K1 / B_KRow, 1, 1, 1, 1, B_K1>,