@inproceedings{anarchitectureforacceleratedlargescale,
  title = {An Architecture for Accelerated Large-Scale Inference of Transformer-Based Language Models},
  author = {Amir Ganiev and Colton Chapin and Anderson de Andrade and Chen Liu},
  year = {2021},
  booktitle = {NAACL 2021 4},
  url = {https://aclanthology.org/2021.naacl-industry.21},
}