@misc{leviathan2022fast, title={Fast Inference from Transformers via Speculative Decoding}, author={Yaniv Leviathan and Matan Kalman and Yossi Matias}, year={2022}, eprint={2211.17192}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2211.17192} }