IST-DASLab/RCO

Mixed-precision quantization for LLMs. Every layer refracts into a different format based on its sensitivity. Native compressed-tensors export, validated on Qwen3.6-35B-A3B MoE with MTP speculative decoding.

State-of-the-art LLM compression, built for production inference with vLLM

Official implementation of LittleBit (NeurIPS 2025) and its follow-up LittleBit-2 (ICML 2026)

LLM quantization optimizer

An Efficient Compression Framework for LLM

Awesome LLM compression research papers and tools.

Awesome LLM pruning papers all-in-one repository with integrating all useful resources and insights.

Python package for LLM compression

Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf and PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression https://arxiv.org/abs/2405.14852