@article{hobbitamixedprecisionexpertoffloading, title = {HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference}, author = {Peng Tang and Jiacheng Liu and Xiaofeng Hou and YiFei PU and Jing Wang and Pheng-Ann Heng and Chao Li and Minyi Guo}, year = {2024}, eprint = {2411.01433}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.01433v2}, }