verifiedhigh · 0.90updated 2026-10-03

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration (Lin et al., MLSys 2024)

paper

Fields

sources/bench-meth-awq

URL

https://arxiv.org/abs/2306.00978

Publisher

arXiv

Kind

paper

Published

2024-01-01

Accessed

2026-10-03

notes

AWQ paper. Tables 1/2/3/4/5 read directly: INT3-g128 and INT4-g128 WikiText perplexity for OPT/LLaMA/Llama-2 plus Mistral-7B and Mixtral-8x7B. Used for the AWQ quality deltas.

Notes

AWQ paper. Tables 1/2/3/4/5 read directly: INT3-g128 and INT4-g128 WikiText perplexity for OPT/LLaMA/Llama-2 plus Mistral-7B and Mixtral-8x7B. Used for the AWQ quality deltas.

Cross-references

This record references no other records.