Ying1123/FlexGen

Running large language models on a single GPU for throughput-oriented scenarios.

682 best points · 264 comments · 1 Hacker News post · 9,340 GitHub stars · View on GitHub

Hacker News discussions

• Running large language models like ChatGPT on a single GPU (682 points, 264 comments, by _nhynes, 2023-02-20)