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
2025-08-23 06:11:24 +08:00
committed by GitHub
parent 11cad1f67b
commit a49a78ffef
351 changed files with 28182 additions and 2032 deletions

View File

@@ -39,14 +39,13 @@
*/
#pragma once
#include "cutlass/cutlass.h"
#include <iostream>
#include <cuda/atomic>
#include <cuda/std/atomic>
#include CUDA_STD_HEADER(atomic)
#include "cute/layout.hpp"
#include "cute/tensor.hpp"
#include "cutlass/cutlass.h"
#include "cutlass/cuda_host_adapter.hpp"