@article{expertflowadaptiveexpertschedulingandmem, title = {ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference}, author = {Zixu Shen and Kexin Chu and Yifan Zhang and Dawei Xiang and Runxin Wu and Wei Zhang}, year = {2025}, eprint = {2510.26730}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.26730}, }