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] Matmul utils initial commit (#2441)

Browse Source
This commit is contained in:
Angelos Katharopoulos
2025-08-01 14:22:25 -07:00
committed by GitHub
parent 86258f292f
commit be9bc96da4
32 changed files with 856 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
mlx/backend/cuda/compiled.cpp
View File

@@ -334,7 +334,7 @@ void Compiled::eval_gpu(
auto kernel = mod.get_kernel(kernel_name);
auto [num_blocks, block_dims] =
get_launch_args(outputs[0], large, work_per_thread);
encoder.add_kernel_node(kernel, num_blocks, block_dims, args.args());
encoder.add_kernel_node(kernel, num_blocks, block_dims, 0, args.args());
}
} // namespace mlx::core