TokenRing: An Efficient Parallelism Framework for Infinite-Context LLMs via Bidirectional Communication

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zongwu, Liu, Fangxin, Li, Mingshuai, Jiang, Li
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!