@article{fastdistributedinferenceservingforlarge, title = {Fast Distributed Inference Serving for Large Language Models}, author = {Bingyang Wu and Yinmin Zhong and Zili Zhang and Shengyu Liu and Fangyue Liu and Yuanhang Sun and Gang Huang and Xuanzhe Liu and Xin Jin}, year = {2023}, eprint = {2305.05920}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2305.05920v3}, }