Matmul() using PyTorch's MPS back end is faster than Apple's MLX
kevinmartinjose.com
Matmul() using PyTorch's MPS back end is faster than Apple's MLX
1–2 of 2 posts
Re: Matmul() using PyTorch's MPS back end is faster than Apple's MLX
#2I have noticed the same thing with PyTorch and MLX.