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

MX GEMM - Add MX BF8 example (#2071)

Browse Source 
* Add MX GEMM example for MX BF8

* Verified MX FP8 with 16x16x128 scale builtin

* Verify MX BF8 GEMM with BF16 output
This commit is contained in:
Andriy Roshchenko
2025-04-16 15:25:02 -06:00
committed by GitHub
parent 3bb62f16cd
commit da54464cce
5 changed files with 139 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_v3_mx.hpp
View File

@@ -699,6 +699,9 @@ struct DeviceGemmMX_Xdl_CShuffleV3 : public DeviceGemmMX<ALayout,
static_assert(ScaleBlockSize == 32, "Only ScaleBlockSize 32 is supported");
static_assert(is_same_v<ComputeTypeA, ADataType> && is_same_v<ComputeTypeB, BDataType>,
"ComputeTypeA and ComputeTypeB must be the same as ADataType and BDataType");
return true;
}