Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jeon, Wonseok, Gagrani, Mukul, Goel, Raghavv, Park, Junyoung, Lee, Mingu, Lott, Christopher
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2402.14160