update 3.8 v2 (#2112)

* update 3.8 v2 * update 3.8 --------- Co-authored-by: yuzhai <yuzhai@nvidia.com>
2025-02-19 22:03:14 -05:00
parent e9627ce55b
commit b84e9802d8
166 changed files with 3986 additions and 4037 deletions
@@ -41,7 +41,6 @@
 #pragma once

 #include <cuda/std/cassert>
-
 #include "cutlass/cutlass.h"
 #include "cutlass/fast_math.h"
 #include "cutlass/layout/pitch_linear.h"