CommitMoE: Efficient Fallback-Free MoE Inference with Offloading Under GPU Memory Constraints - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Han Li, Jingwei Sun 0001, Junqing Lin, Guangzhong Sun. CommitMoE: Efficient Fallback-Free MoE Inference with Offloading Under GPU Memory Constraints. In Sven Koenig, Chad Jenkins, Matthew E. Taylor, editors, Fortieth AAAI Conference on Artificial Intelligence, Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence, Sixteenth Symposium on Educational Advances in Artificial Intelligence, AAAI 2026, Singapore, January 20-27, 2026. pages 22904-22912, AAAI Press, 2026. [doi]

This author has not been identified. Look up 'Han Li' in GoogleThis author has not been identified. Look up 'Jingwei Sun 0001' in GoogleThis author has not been identified. Look up 'Junqing Lin' in GoogleThis author has not been identified. Look up 'Guangzhong Sun' in Google

runs on WebDSL