ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-03 13:11:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Post-merge fix of PR 1300 (#1313)

Browse Source 
* add f8 gemm with multiD for both row/col wise

* change compute_type to fp8

* changed tuning parameters in the example

* add rcr example

* post-merge fix

* fix

* reduce init range
This commit is contained in:
zjing14
2024-06-01 00:46:41 -05:00
committed by GitHub
parent 34f3dfdd61
commit 6fb1f4e03f
3 changed files with 14 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle_v3.hpp
View File

@@ -83,7 +83,7 @@ struct DeviceGemmMultiD_Xdl_CShuffle_V3 : public DeviceGemmMultipleD<ALayout,
static constexpr index_t NumDTensor = DsDataType::Size();
// GridwiseGemm
using GridwiseGemm = GridwiseGemm_xdl_cshuffle_v3<
using GridwiseGemm = GridwiseGemmMultiD_xdl_cshuffle_v3<
ALayout,
BLayout,
DsLayout,