vLLM-readme-2.bib
· 391 B · BibTeX
Raw
@inproceedings{kwon2023efficient,
title={Efficient Memory Management for Large Language Model Serving with PagedAttention},
author={Woosuk Kwon and Zhuohan Li and Siyuan Zhuang and Ying Sheng and Lianmin Zheng and Cody Hao Yu and Joseph E. Gonzalez and Hao Zhang and Ion Stoica},
booktitle={Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles},
year={2023}
}
| 1 | @inproceedings{kwon2023efficient, |
| 2 | title={Efficient Memory Management for Large Language Model Serving with PagedAttention}, |
| 3 | author={Woosuk Kwon and Zhuohan Li and Siyuan Zhuang and Ying Sheng and Lianmin Zheng and Cody Hao Yu and Joseph E. Gonzalez and Hao Zhang and Ion Stoica}, |
| 4 | booktitle={Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles}, |
| 5 | year={2023} |
| 6 | } |