v3.9 update (#2203)

* v3.9 update

* voidD

---------

Co-authored-by: yuzhai <yuzhai@nvidia.com>
This commit is contained in:
Yujia Zhai
2025-04-02 15:11:18 -04:00
committed by GitHub
co-authored by yuzhai
parent 62750a2b75
commit 6f4921858b
129 changed files with 7719 additions and 2036 deletions
@@ -68,6 +68,7 @@ struct IsCutlass3ArrayKernel<ProblemShape, cute::void_t<typename ProblemShape::U
#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"
#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/sm120_gemm_tma_warpspecialized_cooperative_asymmetric_dma.hpp"
////////////////////////////////////////////////////////////////////////////////