@inproceedings{kwon2023pagedattention,
  title = {Efficient Memory Management for Large Language Model Serving with {PagedAttention}},
  author = {Kwon, Woosuk and Li, Zhuohan and Zhuang, Siyuan and Sheng, Ying and Zheng, Lianmin and Yu, Cody Hao and Gonzalez, Joseph E. and Zhang, Hao and Stoica, Ion},
  booktitle = {Proceedings of the 29th Symposium on Operating Systems Principles},
  pages = {611--626},
  year = {2023},
  publisher = {Association for Computing Machinery},
  doi = {10.1145/3600006.3613165},
  url = {https://dl.acm.org/doi/10.1145/3600006.3613165}
}

@inproceedings{zhang2023h2o,
  title = {{H2O}: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models},
  author = {Zhang, Zhenyu and Sheng, Ying and Zhou, Tianyi and Chen, Tianlong and Zheng, Lianmin and Cai, Ruisi and Song, Zhao and Tian, Yuandong and R{\'e}, Christopher and Barrett, Clark and Wang, Zhangyang and Chen, Beidi},
  booktitle = {Advances in Neural Information Processing Systems 36},
  year = {2023},
  url = {https://proceedings.neurips.cc/paper_files/paper/2023/hash/6ceefa7b15572587b78ecfcebb2827f8-Abstract-Conference.html}
}

@inproceedings{li2024snapkv,
  title = {{SnapKV}: {LLM} Knows What You are Looking for Before Generation},
  author = {Li, Yuhong and Huang, Yingbing and Yang, Bowen and Venkitesh, Bharat and Locatelli, Acyr and Ye, Hanchen and Cai, Tianle and Lewis, Patrick and Chen, Deming},
  booktitle = {Advances in Neural Information Processing Systems 37},
  year = {2024},
  doi = {10.52202/079017-0722},
  url = {https://proceedings.neurips.cc/paper_files/paper/2024/hash/28ab418242603e0f7323e54185d19bde-Abstract-Conference.html}
}

@inproceedings{zhao2025semsharekv,
  title = {{SemShareKV}: Efficient {KVCache} Sharing for Semantically Similar Prompts via Token-Level {LSH} Matching},
  author = {Zhao, Xinye and Mastorakis, Spyridon},
  booktitle = {Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics},
  pages = {432--445},
  year = {2025},
  publisher = {The Asian Federation of Natural Language Processing and The Association for Computational Linguistics},
  doi = {10.18653/v1/2025.findings-ijcnlp.25},
  url = {https://aclanthology.org/2025.findings-ijcnlp.25/}
}