Awq Quantization

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

bishal-pdMSFT Updated 0 repo stars

File contents

bishal-pdMSFT/msb-skills commit f94a2622ec

Frequently asked questions

npx get-skill add bishal-pdmsft/awq-quantization