ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 06:49:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK_TILE] Fix gemm_quant (#3186)

Browse Source
This commit is contained in:
linqunAMD
2025-11-12 00:23:57 +08:00
committed by GitHub
parent 88e3212fcc
commit 1b1c46e508
13 changed files with 135 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
include/ck_tile/ops/gemm_quant/kernel/gemm_quant_kernel.hpp
View File

@@ -240,7 +240,10 @@ struct QuantGemmKernel
return dim3(TilePartitioner::GridSize(M, N), 1, KBatch);
}
CK_TILE_HOST static constexpr auto BlockSize() { return dim3(kBlockSize); }
CK_TILE_HOST static auto BlockSize()
{
return is_wave32() ? dim3(kBlockSize / 2) : dim3(kBlockSize);
}
CK_TILE_HOST static constexpr QuantGemmKernelArgs
MakeKernelArgs(const QuantGemmHostArgs& hostArgs)