12 papers
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…
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…
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…
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
DeepSeek-AI, Anyi Xu, Bangcai Lin +315
We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSe…
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…
DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference
Yongtong Wu, Shaoyuan Chen, Yinmin Zhong +10
The performance of multi-turn, agentic LLM inference is increasingly dominated by KV-Cache storage I/O rather than computation. In prevalent disaggregated architectures, loading th…