leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

update 3.8 v2 (#2112)

Browse Source 
* update 3.8 v2

* update 3.8

---------

Co-authored-by: yuzhai <yuzhai@nvidia.com>
This commit is contained in:
Yujia Zhai
2025-02-19 19:03:14 -08:00
committed by GitHub
parent e9627ce55b
commit b84e9802d8
166 changed files with 3986 additions and 4037 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/cute/tensor_impl.hpp
View File

@@ -235,7 +235,7 @@ struct Tensor
decltype(auto)
operator()(Coord const& coord) {
if constexpr (has_underscore<Coord>::value) {
auto const& [sliced_layout,offset] = slice_and_offset(coord, layout());
auto [sliced_layout,offset] = slice_and_offset(coord, layout());
return make_tensor(data() + offset, sliced_layout);
} else {
return data()[layout()(coord)];
@@ -249,7 +249,7 @@ struct Tensor
decltype(auto)
operator()(Coord const& coord) const {
if constexpr (has_underscore<Coord>::value) {
auto const& [sliced_layout,offset] = slice_and_offset(coord, layout());
auto [sliced_layout,offset] = slice_and_offset(coord, layout());
return make_tensor(data() + offset, sliced_layout);
} else {
return data()[layout()(coord)];