@inproceedings{ganiev-etal-2021-architecture,
    title = "An Architecture for Accelerated Large-Scale Inference of Transformer-Based Language Models",
    author = "Ganiev, Amir  and
      Chapin, Colton  and
      De Andrade, Anderson  and
      Liu, Chen",
    editor = "Kim, Young-bum  and
      Li, Yunyao  and
      Rambow, Owen",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2021.naacl-industry.21/",
    doi = "10.18653/v1/2021.naacl-industry.21",
    pages = "163--169"
}