@misc{li2024optimizing, title={Optimizing Mixture-of-Experts Inference Time Combining Model Deployment and Communication Scheduling}, author={Jialong Li and Shreyansh Tripathi and Lakshay Rastogi and Yiming Lei and Rui Pan and Yiting Xia}, year={2024}, eprint={2410.17043}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2410.17043} }