@article{dsdadistributedspeculativedecodingsoluti,
  title = {DSD: A Distributed Speculative Decoding Solution for Edge-Cloud Agile Large Model Serving},
  author = {Fengze Yu and Leshu Li and Brad McDanel and Sai Qian Zhang},
  year = {2025},
  eprint = {2511.21669},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.21669},
}