@misc{shoeybi2019megatron,
  title={Megatron-LM: Training Multi-Billion Parameter Language Models Using GPU Model Parallelism},
  author={Mohammad Shoeybi and Mostofa Patwary and Raul Puri and Patrick LeGresley and Jared Casper and Bryan Catanzaro},
  year={2019},
  eprint={1909.08053},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/1909.08053}
}