@article{mixllmllmquantizationwithglobalmixed, title = {MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design}, author = {Zhen Zheng and Xiaonan Song and Chuanjie Liu}, year = {2024}, eprint = {2412.14590}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.14590v1}, }