leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity

v4.2 release. (#2587)

Browse Source 
* Fix default cluster callback values to 1 to avoid profiler failure when these values are not set in command line.

* v4.2 release.
This commit is contained in:
Junkai-Wu
2025-08-22 18:11:24 -04:00
committed by GitHub
parent 11cad1f67b
commit a49a78ffef
351 changed files with 28182 additions and 2032 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/cutlass/gemm/kernel/gemm_universal.hpp
+5
View File
@@ -68,8 +68,13 @@ struct IsCutlass3ArrayKernel<ProblemShape, cute::void_t<typename ProblemShape::U
#include "cutlass/gemm/kernel/sm100_gemm_tma_warpspecialized_mma_transform.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_tma_warpspecialized_mixed_input_transform.hpp"
#include "cutlass/gemm/kernel/sm100_gemm_array_tma_warpspecialized_input_transform.hpp"
#include "cutlass/gemm/kernel/sm100_gemm_array_tma_warpspecialized_mma_transform.hpp"
#include "cutlass/gemm/kernel/sm100_sparse_gemm_tma_warpspecialized.hpp"
#include "cutlass/gemm/kernel/sm100_gemm_cpasync_warpspecialized.hpp"
#include "cutlass/gemm/kernel/sm103_blockscaled_gemm_tma_warpspecialized.hpp"
#include "cutlass/gemm/kernel/sm103_blockscaled_gemm_array_tma_warpspecialized.hpp"
#include "cutlass/gemm/kernel/sm120_gemm_tma_warpspecialized_cooperative_asymmetric_dma.hpp"
////////////////////////////////////////////////////////////////////////////////