v4.2 release. (#2587)

* 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
+1 -1
View File
@@ -33,8 +33,8 @@
computing reference permutations of 4/5D tensors when source data is column-major.
*/
#pragma once
#include <cuda/std/cassert>
#include "cutlass/cutlass.h"
#include CUDA_STD_HEADER(cassert)
#include "cutlass/layout/pitch_linear.h"
#include "cutlass/layout/matrix.h"
#include "cutlass/coord.h"