mit-han-lab/llm-awq

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

1 best points · 0 comments · 1 Hacker News post · 3,664 GitHub stars · View on GitHub

Hacker News discussions

• New hardware-friendly quantization method (1 points, 0 comments, by theolivenbaum, 2023-06-02)