I-D Action: draft-zhang-rtgwg-llmmoe-multicast-03.txt

Internet-Draft draft-zhang-rtgwg-llmmoe-multicast-03.txt is now available.

   Title:   Multicast use case in LLM MoE
   Authors: Zheng Zhang
            Wei Duan
            Xiaohu Xu
            Yisong Liu
   Name:    draft-zhang-rtgwg-llmmoe-multicast-03.txt
   Pages:   7
   Dates:   2026-08-09

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.

The IETF datatracker status page for this Internet-Draft is:
https://datatracker.ietf.org/doc/draft-zhang-rtgwg-llmmoe-multicast/

There is also an HTML version available at:
https://www.ietf.org/archive/id/draft-zhang-rtgwg-llmmoe-multicast-03.html

A diff from the previous version is available at:
https://author-tools.ietf.org/iddiff?url2=draft-zhang-rtgwg-llmmoe-multicast-03

Internet-Drafts are also available by rsync at:
rsync.ietf.org::internet-drafts


_______________________________________________
I-D-Announce mailing list -- [email protected]
To unsubscribe send an email to [email protected]