Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Timor, Nadav, Mamou, Jonathan, Korat, Daniel, Berchansky, Moshe, Jain, Gaurav, Pereg, Oren, Wasserblat, Moshe, Harel, David
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.05202