@article{layeredgradientaccumulationandmodular,
  title = {Layered gradient accumulation and modular pipeline parallelism: fast and efficient training of large language models},
  author = {Joel Lamy-Poirier},
  year = {2021},
  eprint = {2106.02679},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2106.02679v1},
}