collaborators

6 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

BigMac: Breaking the Pareto Frontier of Compute and Memory in Multimodal LLM Training

Zili Zhang, Chengxu Yang, Shenglong Zhang +8

Training multimodal large language models (MLLMs) is challenged by both model and data heterogeneity. Existing systems redesign the training pipeline to address these challenges, b…

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

HydraServe: Minimizing Cold Start Latency for Serverless LLM Serving in Public Clouds

Chiheng Lou, Sheng Qi, Chao Jin +5

With the proliferation of large language model (LLM) variants, developers are turning to serverless computing for cost-efficient LLM deployment. However, public cloud providers oft…