"EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large ..."

Yunsheng Ni et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2405.07542

access: open

type: Informal or Other Publication

metadata version: 2024-06-15

a service of  Schloss Dagstuhl - Leibniz Center for Informatics