@misc{chen2024sequoia, title={Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding}, author={Zhuoming Chen and Avner May and Ruslan Svirschevski and Yuhsun Huang and Max Ryabinin and Zhihao Jia and Beidi Chen}, year={2024}, eprint={2402.12374}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2402.12374} }