"RTP: Rethinking Tensor Parallelism with Memory Deduplication."

Cheng Luo, Tianle Zhong, Geoffrey Fox (2023)

Details and statistics

DOI: 10.48550/ARXIV.2311.01635

access: open

type: Informal or Other Publication

metadata version: 2023-11-07

a service of  Schloss Dagstuhl - Leibniz Center for Informatics