@article{maximizingparallelismindistributed,
  title = {Maximizing Parallelism in Distributed Training for Huge Neural Networks},
  author = {Zhengda Bian and Qifan Xu and Boxiang Wang and Yang You},
  year = {2021},
  eprint = {2105.14450},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2105.14450v1},
}