Fast transformer inference with Metal Performance Shaders #1 Post by reichardt » Thu, Nov 24, 2022, 11:21 PM UTC Fast transformer inference with Metal Performance Shadersexplosion.ai
Re: Fast transformer inference with Metal Performance Shaders #2 Post by reichardt » Thu, Nov 24, 2022, 11:23 PM UTC Seems like the Apple M1 Max is almost half as fast as a RTX 3090. Pretty cool!