@article{trainingandinferenceoflargelanguage,
  title = {Training and inference of large language models using 8-bit floating point},
  author = {Sergio P. Perez and Yan Zhang and James Briggs and Charlie Blake and Josh Levy-Kramer and Paul Balanca and Carlo Luschi and Stephen Barlow and Andrew William Fitzgibbon},
  year = {2023},
  eprint = {2309.17224},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2309.17224v1},
}