5 papers
PLATONT: Learning a Platonic Representation for Unified Network Tomography
Chengze Du, Heng Xu, Zhiwei Yu +2
Network tomography aims to infer hidden network states, such as link performance, traffic load, and topology, from external observations. Most existing methods solve these problems…
RailS: Load Balancing for All-to-All Communication in Distributed Mixture-of-Experts Training
Heng Xu, Zhiwei Yu, Chengze Du +5
Training Mixture-of-Experts (MoE) models introduces sparse and highly imbalanced all-to-all communication that dominates iteration time. Conventional load-balancing methods fail to…
Temporal-Aware GPU Resource Allocation for Distributed LLM Inference via Reinforcement Learning
Chengze Du, Zhiwei Yu, Heng Xu +3
The rapid growth of large language model (LLM) services imposes increasing demands on distributed GPU inference infrastructure. Most existing scheduling systems follow a reactive p…
REACH: Reinforcement Learning for Efficient Allocation in Community and Heterogeneous Networks
Zhiwei Yu, Chengze Du, Heng Xu +3
Community GPU platforms are emerging as a cost-effective and democratized alternative to centralized GPU clusters for AI workloads, aggregating idle consumer GPUs from globally dis…
RoTO: Robust Topology Obfuscation Against Tomography Inference Attacks
Chengze Du, Heng Xu, Zhiwei Yu +3
Tomography inference attacks aim to reconstruct network topology by analyzing end-to-end probe delays. Existing defenses mitigate these attacks by manipulating probe delays to misl…