PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Hao, Lyu, Mengsi, Chen, Zhuo, Xing, Xingrun, Ao, Yulong, Lin, Yonghua
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!