@misc{pope2022efficiently, title={Efficiently Scaling Transformer Inference}, author={Reiner Pope and Sholto Douglas and Aakanksha Chowdhery and Jacob Devlin and James Bradbury and Anselm Levskaya and Jonathan Heek and Kefan Xiao and Shivani Agrawal and Jeff Dean}, year={2022}, eprint={2211.05102}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2211.05102} }