"SDSAT: Accelerating LLM Inference through Speculative Decoding with ..."

Chengbo Liu, Yong Zhu (2024)

Details and statistics

DOI: 10.48550/ARXIV.2403.18647

access: open

type: Informal or Other Publication

metadata version: 2024-04-10

a service of  Schloss Dagstuhl - Leibniz Center for Informatics