%% You should probably cite draft-zhang-rtgwg-llmmoe-multicast-02 instead of this revision.
@techreport{zhang-rtgwg-llmmoe-multicast-00,
    number =    {draft-zhang-rtgwg-llmmoe-multicast-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-zhang-rtgwg-llmmoe-multicast/00/},
    author =    {Zheng Zhang and Wei Duan},
    title =     {{Multicast usage in LLM MoE}},
    pagetotal = 6,
    year =      ,
    month =     ,
    day =       ,
    abstract =  {Large Language Models (LLMs) have been widely used in recent years. The Mixture of Experts (MoE) architecture is one of the features of LLMs that enables efficient inference and cost-effective training. With the MoE architecture, there are potential multicast use cases such as tokens dispatching. This draft attempts to analyze these use cases.},
}