zhangyiss/mlx
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx.git synced 2025-12-16 01:49:05 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[CUDA] Fix back-end bugs and enable corresponding tests (#2296)

Browse Source 
* Fix some cuda back-end bugs and enable corresponding tests

* more fixes

* enable more tests

* format
This commit is contained in:
Awni Hannun
2025-06-16 08:45:40 -07:00
committed by GitHub
parent 4fda5fbdf9
commit c552ff2451
16 changed files with 115 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
mlx/backend/cuda/copy/copy_contiguous.cu
View File

@@ -43,7 +43,8 @@ void copy_contiguous(
if (ctype == CopyType::Vector) {
kernel = cu::copy_v<InType, OutType, IdxT>;
}
auto [num_blocks, block_dims] = get_launch_args(kernel, out, LARGE);
auto [num_blocks, block_dims] = get_launch_args(
kernel, out.data_size(), out.shape(), out.strides(), LARGE);
kernel<<<num_blocks, block_dims, 0, stream>>>(
in.data<InType>() + in_offset,
out.data<OutType>() + out_offset,