@article{galvatronefficienttransformertrainingove,
  title = {Galvatron: Efficient Transformer Training over Multiple GPUs Using Automatic Parallelism},
  author = {Xupeng Miao and Yujie Wang and Youhe Jiang and Chunan Shi and Xiaonan Nie and Hailin Zhang and Bin Cui},
  year = {2022},
  eprint = {2211.13878},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2211.13878v1},
}