3 papers
cs.DC2026
ExpertPlex: A High-Goodput Disaggregated Serving System for MoE LLMs with Adaptive Persistent Kernels
Bingyang Wu, Chao Jin, Zili Zhang +6
LLMs scale Mixture-of-Experts (MoE) parameters for superior intelligence, but massive weights and dynamic computation impede efficient serving. Existing instance-level prefill-deco…
cs.LG2026
ReLibra: Routing-Replay-Guided Load Balancing for MoE Training in Reinforcement Learning
Chao Jin, Xinming Wei, Yinmin Zhong +6
Load imbalance is a long-standing challenge in Mixture-of-Experts (MoE) training and is exacerbated in reinforcement learning (RL) for LLMs, where hot experts can shift frequently…
cs.DC2025
MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Ruidong Zhu, Ziheng Jiang, Chao Jin +17
Mixture-of-Experts (MoE) showcases tremendous potential to scale large language models (LLMs) with enhanced performance and reduced computational complexity. However, its sparsely…