@article{Li_25,
TITLE = {Optimizing Mixture-of-Experts Inference Time via Model Deployment and Communication Scheduling},
AUTHOR = {Li, Jialong and Tripathi, Shreyansh and Rastogi, Lakshay and Lei, Yiming and Pan, Rui and Xia, Yiting},
LANGUAGE = {eng},
ISSN = {2998-4157},
DOI = {10.1109/TON.2025.3645806},
PUBLISHER = {IEEE},
ADDRESS = {Piscataway, NJ},
YEAR = {2025},
MARGINALMARK = {$\bullet$},
DATE = {2025},
JOURNAL = {IEEE Transactions on Networking},
VOLUME = {34},
PAGES = {2478--2497},
}