@article{scalableandefficientmoetrainingfor,
  title = {Scalable and Efficient MoE Training for Multitask Multilingual Models},
  author = {Young Jin Kim and Ammar Ahmad Awan and Alexandre Muzio and Andres Felipe Cruz Salinas and Liyang Lu and Amr Hendy and Samyam Rajbhandari and Yuxiong He and Hany Hassan Awadalla},
  year = {2021},
  eprint = {2109.10465},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2109.10465v1},
}