(github.com)

548 points nsagent | 1 comments | 14 Jul 25 21:40 UTC | HN request time: 0.211s | source

Show context

Is this for Mac's with NVIDIA cards in them or Apple Metal/Apple Silicon speaking CUDA?... I can't really tell.

Edit: looks like it's "write once, use everywhere". Write MLX, run it on Linux CUDA, and Apple Silicon/Metal.

dkga ◴[14 Jul 25 23:06 UTC] No.44566338[source]▶

This is the only strategy humble me can see working for CUDA in MLX

replies(1): >>44567408 #

1. whatever1 ◴[15 Jul 25 02:48 UTC] No.44567408[source]▶

This is the right answer. Local models will be accelerated by Apple private cloud.

Apple's MLX adding CUDA support