AirLLM 70B inference with single 4GB GPU

AirLLM 70B inference with single 4GB GPU. Contribute to lyogavin/airllm development by creating an account on GitHub.
228 points by Anon84 79 days ago github.com 83 comments
Summary not yet generated for this article.

Comments (83 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open