CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lv, Junlin, Feng, Yuan, Xie, Xike, Jia, Xin, Peng, Qirong, Xie, Guiming
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!