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

CUTLASS 3.4.0 (#1286)

Browse Source 
* CUTLASS 3.4.0

* Update CHANGELOG.md

---------

Co-authored-by: Pradeep Ramani <prramani@nvidia.com>
This commit is contained in:
Pradeep Ramani
2023-12-29 15:21:31 -05:00
committed by GitHub
co-authored by Pradeep Ramani
parent b7508e3379
commit 8236f30675
211 changed files with 11409 additions and 2763 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/cutlass/gemm/kernel/gemm_universal.h
+2 -2
View File
@@ -67,9 +67,9 @@ class GemmUniversal<
Epilogue_,
ThreadblockSwizzle_,
void,
// 3.x kernels use the first template argument to define the ProblemShape tuple
// 3.x kernels use the first template argument to define the ProblemShape
// We use this invariant to SFINAE dispatch against either the 2.x API or the 3.x API
cute::enable_if_t<not cute::is_tuple<Mma_>::value>
cute::enable_if_t<not (cute::is_tuple<Mma_>::value || IsCutlass3ArrayKernel<Mma_>::value)>
> {
public: