News for hackers. Stuff that matters.
Re:AMD's MI300X Outperforms Nvidia's H100 for LLM Inference by irusensei on Thursday June 13, 2024 @05:49AM (#40667684)
Every hardware vendor is working to provide something with their own technology. I don't know if it's possible but a lot of very resourceful companies are doing their best to break the CUDA dominance. I really hope it works and hopefully a non proprietary standard emerges.

There are no comments on this comment yet.