Serving 70B-scale LLMs efficiently on low-resource edge devices [pdf]
📰 Hacker News · simonpure
Serving 70B-scale LLMs efficiently on low-resource edge devices [pdf]. 58 comments, 248 points on Hacker News.
Serving 70B-scale LLMs efficiently on low-resource edge devices [pdf]. 58 comments, 248 points on Hacker News.