Jing Yang, Huaqing Tu, Gongming Zhao, Hongli Xu 0001, Baoqing Wang, Long Li. Dynamic Hot Expert Replication with Load and Topology-Aware Joint Gating for Distributed MoE Inference. In IEEE/ACM International Symposium on Quality of Service, IWQoS 2026, Istanbul, Turkiye, June 29 - July 2, 2026. pages 1-6, IEEE, 2026. [doi]
Abstract is missing.