Hacker News new | past | comments | ask | show | jobs | submit | from login
Exllamav2: Inference library for running LLMs locally on consumer-class GPUs (github.com/turboderp)
322 points by Palmik on Sept 13, 2023 | past | 125 comments
ExLlama: Memory efficient way to run Llama (github.com/turboderp)
3 points by Palmik on Aug 16, 2023 | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: