@misc{park2024precision, title={Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs}, author={Yeonhong Park and Jake Hyun and SangLyul Cho and Bonggeun Sim and Jae W. Lee}, year={2024}, eprint={2402.10517}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2402.10517} }