vllm-project/llm-compressor

State-of-the-art LLM compression, built for production inference with vLLM

1 best points · 1 comments · 1 Hacker News post · 3,950 GitHub stars · View on GitHub

Hacker News discussions

• LLM compressor: compress models for efficient deployment (1 points, 1 comments, by hajduksplit, 2024-08-20)