Xiaonan Nie, Xupeng Miao, Zilong Wang, Zichao Yang, Jilong Xue, Lingxiao Ma, Gang Cao, Bin Cui 0001. FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement. Proc. ACM Manag. Data, 1(1), 2023. [doi]
@article{NieMWYXMC023, title = {FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement}, author = {Xiaonan Nie and Xupeng Miao and Zilong Wang and Zichao Yang and Jilong Xue and Lingxiao Ma and Gang Cao and Bin Cui 0001}, year = {2023}, doi = {10.1145/3588964}, url = {https://doi.org/10.1145/3588964}, researchr = {https://researchr.org/publication/NieMWYXMC023}, cites = {0}, citedby = {0}, journal = {Proc. ACM Manag. Data}, volume = {1}, number = {1}, }