activity
20242026
collaborators

8 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.DC2026

UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing

Xinming Wei, Chao Jin, Tuo Dai +10

Large-scale expert parallelism (EP) is becoming pivotal for training and serving frontier MoE models, but it also amplifies device-level expert load imbalance into compute straggle…

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.LG2026

Heddle: A Distributed Orchestration System for Agentic RL Rollout

Zili Zhang, Yinmin Zhong, Chengxu Yang +5

Agentic Reinforcement Learning (RL) enables LLMs to solve complex tasks by alternating between a data-collection rollout phase and a policy training phase. During rollout, the agen…

cs.DC2025

TokenLake: A Unified Segment-level Prefix Cache Pool for Fine-grained Elastic Long-Context LLM Serving

Bingyang Wu, Zili Zhang, Yinmin Zhong +4

Prefix caching is crucial to accelerate multi-turn interactions and requests with shared prefixes. At the cluster level, existing prefix caching systems are tightly coupled with re…

cs.LG2025

StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation

Yinmin Zhong, Zili Zhang, Xiaoniu Song +11

Reinforcement learning (RL) has become the core post-training technique for large language models (LLMs). RL for LLMs involves two stages: generation and training. The LLM first ge…