Dynamic-Width Speculative Beam Decoding for Efficient LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qin, Zongyue, He, Zifan, Prakriya, Neha, Cong, Jason, Sun, Yizhou
Format:	Preprint
Published:	2024
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2409.16560