Hqq Quantization

Quantize LLMs to 8/4/3/2/1-bit precision without calibration data, using multiple backends and HuggingFace/vLLM integration.

qhjqhj00 Updated 3 repo stars

File contents

qhjqhj00/research-skills-pool commit 4a73b9b1a5

Frequently asked questions

npx get-skill add qhjqhj00/hqq-quantization