"SMILE: Scaling Mixture-of-Experts with Efficient Bi-level Routing."

Chaoyang He et al. (2022)

Details and statistics

DOI: 10.48550/ARXIV.2212.05191

access: open

type: Informal or Other Publication

metadata version: 2023-11-12

a service of  Schloss Dagstuhl - Leibniz Center for Informatics