Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Jingyu, Chen, Beidi, Zhang, Ce
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.02789