Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design.
Mohan Zhang, Pingzhi Li, Jie Peng, Mufan Qiu, Tianlong Chen
Browse the full NAACL paper archive.
Mohan Zhang, Pingzhi Li, Jie Peng, Mufan Qiu, Tianlong Chen
Browse the full NAACL paper archive.