Fate: Fasss sEsdge Inference of Mixture-of-Experts Models via Cross-Layer Gate.

@inproceedings{fang-2026-fate, author = {Zhiyuan Fang and Xingfan Yu and Yuegui Huang and Zicong Hong and Yufeng Lyu and Wuhui Chen and Yue Yu and Fan Yu}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{Fate: Fasss sEsdge Inference of Mixture-of-Experts Models via Cross-Layer Gate}}, booktitle = {{Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026}}, pages = {5537--5546}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3792527}, doi = {https://doi.org/10.1145/3774904.3792527} }