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 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

3
mlx/backend/cuda/binary_two.cu
View File

@@ -238,6 +238,7 @@ void binary_two_op_gpu_inplace(
dims_constant()>,
num_blocks,
block_dims,
0,
a.data<InType>(),
b.data<InType>(),
out_a.data<OutType>(),
@@ -254,6 +255,7 @@ void binary_two_op_gpu_inplace(
cu::binary_two_g<Op, InType, OutType, IdxT>,
num_blocks,
block_dims,
0,
a.data<InType>(),
b.data<InType>(),
out_a.data<OutType>(),
@@ -287,6 +289,7 @@ void binary_two_op_gpu_inplace(
kernel,
num_blocks,
block_dims,
0,
a.data<InType>(),
b.data<InType>(),
out_a.data<OutType>(),