@inproceedings{cs-19-1,
  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 and Zhang, Hao and Stoica, Ion},
  booktitle = {Proceedings of the 29th Symposium on Operating Systems Principles},
  year = {2023},
  doi = {10.1145/3600006.3613165},
  url = {https://arxiv.org/abs/2309.06180}
}

@inproceedings{cs-19-2,
  title = {{FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness}},
  author = {Dao, Tri and Fu, Daniel Y. and Ermon, Stefano and Rudra, Atri and Re, Christopher},
  booktitle = {Advances in Neural Information Processing Systems 35},
  year = {2022},
  url = {https://arxiv.org/abs/2205.14135}
}

@inproceedings{cs-19-3,
  title = {{Orca: A Distributed Serving System for Transformer-Based Generative Models}},
  author = {Yu, Gyeong-In and Jeong, Joo Seong and Kim, Geon-Woo and Kim, Soojeong and Chun, Byung-Gon},
  booktitle = {USENIX OSDI},
  year = {2022},
  url = {https://www.usenix.org/conference/osdi22/presentation/yu}
}