@techreport{li-moe-ep-communication-optimization-00,
    number =    {draft-li-moe-ep-communication-optimization-00},
    type =      {Internet-Draft},
    institution =   {Internet Engineering Task Force},
    publisher = {Internet Engineering Task Force},
    note =      {Work in Progress},
    url =       {https://datatracker.ietf.org/doc/draft-li-moe-ep-communication-optimization/00/},
    author =    {Zhiqiang Li and Zongpeng Du and Junjie Wang and Wei Cheng and Guoying Zhang and Xun Sun and Chunhao Zhao},
    title =     {{Communication Optimization for MoE Expert Parallelism in Distributed Training}},
    pagetotal = 10,
    year =      2026,
    month =     jul,
    day =       4,
    abstract =  {This document describes a communication optimization mechanism for Mixture of Experts (MoE) Expert Parallelism (EP) in distributed training environments. It defines two core mechanisms: (1) an adaptive communication mode selection that dynamically chooses between Data-Centric and Expert-Centric All-to-All communication patterns based on a comparison of expert parameter size versus token data size, minimizing cross-node communication volume; (2) a priority-based co-scheduling strategy for All-to-All and AllReduce collective communications, combined with chunked transmission and in- network aggregation acceleration, to eliminate bandwidth contention and reduce overall training latency.},
}