Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Seongjun, Lee, Gibbeum, Cho, Jaewoong, Papailiopoulos, Dimitris, Lee, Kangwook
Format:	Preprint
Published:	2023
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2307.05908