"Sparse Backpropagation for MoE Training."

Liyuan Liu, Jianfeng Gao, Weizhu Chen (2023)

Details and statistics

DOI: 10.48550/ARXIV.2310.00811

access: open

type: Informal or Other Publication

metadata version: 2024-04-11

a service of  Schloss Dagstuhl - Leibniz Center for Informatics