@article{duetserveharmonizingprefillanddecodeforl,
  title = {DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing},
  author = {Lei Gao and Chaoyi Jiang and Hossein Entezari Zarch and Daniel Wong and Mark Hill and Murali Annavaram},
  year = {2025},
  eprint = {2511.04791},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.04791},
}