PARD: Enhancing Goodput for Inference Pipeline via Proactive Request Dropping

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Zhixin, Hu, Yitao, Chen, Simin, Ji, Mingfang, Yang, Wei, Zhang, Yuhao, Zhao, Laiping, Li, Wenxin, Liu, Xiulong, Qu, Wenyu, Wang, Hao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!