Source · Tier A · Peer-reviewedSource · Efficient Memory Management for Large Language Model Serving with PagedAttention
Efficient Memory Management for Large Language Model Serving with PagedAttention
W. Kwon, Z. Li, S. Zhuang, Y. Sheng, L. Zheng, C. H. Yu, J. E. Gonzalez, H. Zhang, I. Stoica. 2023. Proceedings of the 29th Symposium on Operating Systems Principles (SOSP 2023).
| Original | https://doi.org/10.1145/3600006.3613165 |
|---|---|
| Archived copy | https://arxiv.org/abs/2309.06180 |
| DOI | 10.1145/3600006.3613165 |
| arXiv | 2309.06180 |
| Version | Assessed the full arXiv v1 HTML (12 September 2023), especially §2.2 on autoregressive generation, §3 on memory use and §4.4 on shared prefixes. The text identifies the SOSP 2023 publication and DOI. |
| Accessed | 2026-10-27 |
Cited by
- KV cacheConcept