A Switch-Centric In-Network Architecture for Accelerating LLM Inference in Shared-Memory Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Aojie, Zhu, Kang, Zhang, Zhiheng, Su, Zhengxu, Liu, Juntao, Du, Yuan, Du, Li
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!