Characterizing CPU-Induced Slowdowns in Multi-GPU LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chung, Euijun, Jia, Yuxiao, Jezghani, Aaron, Kim, Hyesoon
Format:	Preprint
Published:	2026
Subjects:	Hardware Architecture 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/2603.22774