CUTLASS 3.6.0 (#1850)

* v3.6 * update changelog * update readme * fix typo * fixing typos * hopper gemm with weight prefetch --------- Co-authored-by: yuzhai <yuzhai@nvidia.com> Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
2024-10-09 15:33:27 -04:00
parent 0837a2a00a
commit cc3c29a81a
354 changed files with 105937 additions and 8197 deletions
@@ -31,12 +31,14 @@
 #pragma once

 #include <cute/config.hpp>
-
-#include <cute/atom/copy_atom.hpp>
-#include <cute/algorithm/copy.hpp>
-
-#include <cute/tensor_impl.hpp>
+#include <cute/layout.hpp>
+#include <cute/layout_composed.hpp> // cute::logical_divide
+#include <cute/swizzle.hpp>         // cute::Swizzle
+#include <cute/swizzle_layout.hpp>  // cute::get_nonswizzle_portion
+#include <cute/tensor_impl.hpp>     // cute::Tensor
 #include <cute/tensor_predicate.hpp>
+#include <cute/algorithm/copy.hpp>
+#include <cute/atom/copy_atom.hpp>

 namespace cute
 {