IST-DASLab/GSQ

Statistically-Lossless Quantization of Large Language Models

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

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

ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization

[ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs

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

Making 1.58-bit models simple to build and broadly accessible through low-cost, high-accuracy post-training ternary quantization.

[ICML 2024 Oral] This project is the official implementation of our Accurate LoRA-Finetuning Quantization of LLMs via Information Retention

Accessible large language models via k-bit quantization for PyTorch.