leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 30 Packages Projects Releases Wiki Activity

v3.8.0 update (#2082)

Browse Source 
* 3.8 update

* fix Markus' name

---------

Co-authored-by: yuzhai <yuzhai@nvidia.com>
This commit is contained in:
Yujia Zhai
2025-02-06 21:33:40 -05:00
committed by GitHub
co-authored by yuzhai
parent affd1b693d
commit 833f6990e0
168 changed files with 24945 additions and 3436 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/cutlass/gemm/kernel/gemm_universal.hpp
+6 -2
View File
@@ -63,6 +63,10 @@ struct IsCutlass3ArrayKernel<ProblemShape, cute::void_t<typename ProblemShape::U
#include "cutlass/gemm/kernel/sm90_gemm_tma_warpspecialized_cooperative.hpp"
#include "cutlass/gemm/kernel/sm90_gemm_array_tma_warpspecialized_pingpong.hpp"
#include "cutlass/gemm/kernel/sm90_gemm_array_tma_warpspecialized_cooperative.hpp"
#include "cutlass/gemm/kernel/sm100_gemm_tma_warpspecialized.hpp"
#include "cutlass/gemm/kernel/sm100_gemm_array_tma_warpspecialized.hpp"
#include "cutlass/gemm/kernel/sm100_gemm_tma_warpspecialized.hpp"
#include "cutlass/gemm/kernel/sm100_gemm_array_tma_warpspecialized.hpp"
#include "cutlass/gemm/kernel/sm100_gemm_tma_warpspecialized_input_transform.hpp"
#include "cutlass/gemm/kernel/sm100_gemm_array_tma_warpspecialized_input_transform.hpp"
////////////////////////////////////////////////////////////////////////////////