News for hackers. Stuff that matters.
Re:What lengths will Chinese companies go to get an Nvidia A... by cthalupa on Tuesday February 27, 2024 @02:04AM (#39520982)
You don't need nvlink for inference with models that need to fit in multiple cards. I'm using a laptop with a 3080 ti mobile and a 3090 in an eGPU enclosure for running LLM models over 24GB.

There are no comments on this comment yet.