QuixiAI/laserRMT

The official implementation of the paper "Uncovering the Redundancy in Transformers via a Unified Study of Layer Dropping (TMLR)".

Awesome LLM compression research papers and tools.

Python package for LLM compression

Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.

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

The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

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)

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.