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
+6 -6
View File
@@ -29,13 +29,13 @@
*
**************************************************************************************************/
#pragma once
#include "cutlass/cutlass.h"
#if defined(__CUDACC_RTC__)
#include <cuda/std/type_traits>
#include <cuda/std/utility>
#include <cuda/std/cstddef>
#include <cuda/std/cstdint>
#include <cuda/std/limits>
#include CUDA_STD_HEADER(type_traits)
#include CUDA_STD_HEADER(utility)
#include CUDA_STD_HEADER(cstddef)
#include CUDA_STD_HEADER(cstdint)
#include CUDA_STD_HEADER(limits)
#else
#include <type_traits>
#include <utility> // tuple_size, tuple_element