ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-06-29 19:28:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

hot fix moe gemm2

Browse Source
This commit is contained in:
coderfeli
2025-03-05 09:34:56 +00:00
parent 31994ea8bb
commit 08e902e2fa
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/grid/gridwise_moe_gemm.hpp
View File

@@ -1492,7 +1492,7 @@ struct GridwiseMoeGemm
using CDEBlockTransferCluster =
CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock;
const auto EGlobalMemoryDataOperation = CGlobalMemoryDataOperation;
constexpr index_t scatter_weight_idx = 1;
constexpr index_t scatter_weight_idx = IsInputGemm ? 1 : 3; // hack fix felix
auto cde_block_copy_lds_and_global = ThreadGroupTensorSliceTransfer_v7r3_scatter<
ThisThreadBlock,
decltype(container_concat(make_tuple(CShuffleDataType{}), DsDataType{})),
@@ -2000,7 +2000,7 @@ struct GridwiseMoeGemm
using CDEBlockTransferCluster =
CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock;
const auto EGlobalMemoryDataOperation = CGlobalMemoryDataOperation;
constexpr index_t scatter_weight_idx = 1;
constexpr index_t scatter_weight_idx = IsInputGemm ? 1 : 3; // hack fix felix
auto cde_block_copy_lds_and_global = ThreadGroupTensorSliceTransfer_v7r3_scatter<
ThisThreadBlock,
decltype(container_concat(make_tuple(CShuffleDataType{}), DsDataType{})),