Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference.
Baihui Liu, Kaiyuan Tian, Wei Wang, Zhaoning Zhang, Linbo Qiao, Dongsheng Li
Browse the full ACL paper archive.
Baihui Liu, Kaiyuan Tian, Wei Wang, Zhaoning Zhang, Linbo Qiao, Dongsheng Li
Browse the full ACL paper archive.