papers.bib

---
---

```bib
@article{Liang2025InjectingAI,
  bibtex_show={true},
  pdf={https://arxiv.org/pdf/2503.20552},
  code={https://github.com/ASISys/Adrenaline},
  selected={true},
  title={Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation},
  author={Yunkai Liang† and Zhangyu Chen† and Pengfei Zuo and Zhi Zhou and Xu Chen and Zhou Yu},
  journal={arXiv preprint arXiv:2503.20552},
  year={2025},
  abbr={arXiv}
}

@article{Zhou2025ProgressiveSA,
  bibtex_show={true},
  pdf={https://arxiv.org/pdf/2503.00392},
  selected={true},
  title={Progressive Sparse Attention: Algorithm and System Co-design for Efficient Attention in LLM Serving},
  author={Qihui Zhou and Peiqi Yin and Pengfei Zuo and James Cheng},
  journal={arXiv preprint arXiv:2503.00392},
  year={2025},
  abbr={arXiv}
}

@inproceedings{He2025AdaSkipAS,
  bibtex_show={true},
  pdf={https://arxiv.org/pdf/2501.02336},
  code={https://github.com/ASISys/AdaSkip},
  selected={true},
  title={AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference},
  author={Zhuomin He† and Yizhen Yao† and Pengfei Zuo and Bin Gao and Qinya Li and Zhenzhe Zheng and Fan Wu},
  booktitle={Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence (AAAI)},
  year={2025},
  abbr={AAAI}
}

@inproceedings{Gao2024CostEfficientLL,
  bibtex_show={true},
  pdf={https://www.usenix.org/system/files/atc24-gao-bin-cost.pdf},
  video={https://www.usenix.org/conference/atc24/presentation/gao-bin-cost},
  selected={true},
  title={Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention},
  author={Bin Gao and Zhuomin He and Puru Sharma and Qingxuan Kang and Djordje Jevdjic and Junbo Deng and Xingkun Yang and Zhou Yu and Pengfei Zuo},
  booktitle={Proceedings of the 2024 USENIX Annual Technical Conference (USENIX ATC)},
  year={2024},
  abbr={USENIX ATC}
}
```