"EdgeMoE: Fast On-Device Inference of MoE-based Large Language Models."

Rongjie Yi et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2308.14352

access: open

type: Informal or Other Publication

metadata version: 2023-09-01

a service of  Schloss Dagstuhl - Leibniz Center for Informatics