@article{adaserveslocustomizedllmservingwithfine,
  title = {AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding},
  author = {Zikun Li and Zhuofu Chen and Remi Delacourt and Gabriele Oliaro and Zeyu Wang and Qinghan Chen and Shuhuai Lin and April Yang and Zhihao Zhang and Zhuoming Chen and Sean Lai and Xinhao Cheng and Xupeng Miao and Zhihao Jia},
  year = {2025},
  eprint = {2501.12162},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.12162v2},
}