@misc{dettmers2022matrix, title={LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale}, author={Tim Dettmers and Mike Lewis and Younes Belkada and Luke Zettlemoyer}, year={2022}, eprint={2208.07339}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2208.07339} }