gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Guo, Tianyu, Zhang, Xianwei, Du, Jiangsu, Chen, Zhiguang, Xiao, Nong, Lu, Yutong
Format:	Preprint
Published:	2025
Subjects:	Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2504.14775