@article{optimizingspeculativedecodingforserving, title = {Optimizing Speculative Decoding for Serving Large Language Models Using Goodput}, author = {Xiaoxuan Liu and Cade Daniel and Langxiang Hu and Woosuk Kwon and Zhuohan Li and Xiangxi Mo and Alvin Cheung and Zhijie Deng and Ion Stoica and Hao Zhang}, year = {2024}, eprint = {2406.14066}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.14066v2}, }