@article{specinferacceleratinggenerativellmservin,
  title = {SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification},
  author = {Xupeng Miao and Gabriele Oliaro and Zhihao Zhang and Xinhao Cheng and Zeyu Wang and Zhengxin Zhang and Rae Ying Yee Wong and Alan Zhu and Lijie Yang and Xiaoxiang Shi and Chunan Shi and Zhuoming Chen and Daiyaan Arfeen and Reyna Abhyankar and Zhihao Jia},
  year = {2023},
  eprint = {2305.09781},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.09781v4},
}