BirdMoE: Reducing Communication Costs for Mixture-of-Experts Training Using Load-Aware Bi-random Quantization.
Donglei Wu, Weihao Yang, Xiangyu Zou, Jinda Jia, Dingwen Tao, Wen Xia, Zhihong Tian
Browse the full DAC paper archive.
Donglei Wu, Weihao Yang, Xiangyu Zou, Jinda Jia, Dingwen Tao, Wen Xia, Zhihong Tian
Browse the full DAC paper archive.