DynaMo: Accelerating Language Model Inference with Dynamic Multi-Token Sampling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tuli, Shikhar, Lin, Chi-Heng, Hsu, Yen-Chang, Jha, Niraj K., Shen, Yilin, Jin, Hongxia
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2405.00888