ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-03 05:01:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix mxfp8-gemm example failure (#3531)

Browse Source 
Co-authored-by: ZheWang <zhewan@amd.com>
This commit is contained in:
ZheWang
2026-01-13 10:26:45 +08:00
committed by GitHub
parent 5aaa031350
commit a575acb245
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
include/ck_tile/ops/epilogue/cshuffle_epilogue.hpp
View File

@@ -331,10 +331,15 @@ struct CShuffleEpilogue
}
else
{
#if defined(__gfx950__)
constexpr auto is_950 = true;
#else
constexpr auto is_950 = false;
#endif
constexpr int RakedXDLN_PerWarp = NumNXdlPerWavePerShuffle / BlockedXDLN_PerWarp;
// BlockedLayout
// this branch is for original a16w4
if constexpr(is_any_of<ADataType, pk_int4_t, pk_fp4_t>::value ||
if constexpr(is_950 || is_any_of<ADataType, pk_int4_t, pk_fp4_t>::value ||
is_any_of<BDataType, pk_int4_t, pk_fp4_t>::value)
{
return tile_distribution_encoding<