"S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for ..."

Wei Zhong, Manasa Bharadwaj (2024)

Details and statistics

DOI: 10.48550/ARXIV.2405.20314

access: open

type: Informal or Other Publication

metadata version: 2024-06-24

a service of  Schloss Dagstuhl - Leibniz Center for Informatics