Skip to content

awq-quantization

from Orchestra-Research/AI-research-SKILLs

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

v1.0.0MIT
311
Lines
1,035
Words
15
Code Blocks

Languages

bashpython
10-optimization/awq/SKILL.md