@misc{chen2024magicdec, title={MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding}, author={Jian Chen and Vashisth Tiwari and Ranajoy Sadhukhan and Zhuoming Chen and Jinyuan Shi and Ian En-Hsu Yen and Beidi Chen}, year={2024}, eprint={2408.11049}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2408.11049} }