TY  - CONF
ID  - cs-19-1
TI  - Efficient Memory Management for Large Language Model Serving with PagedAttention
AU  - Kwon, Woosuk
AU  - Li, Zhuohan
AU  - Zhuang, Siyuan
AU  - Sheng, Ying
AU  - Zheng, Lianmin
AU  - Yu, Cody Hao
AU  - Gonzalez, Joseph
AU  - Zhang, Hao
AU  - Stoica, Ion
T2  - Proceedings of the 29th Symposium on Operating Systems Principles
PY  - 2023
DO  - 10.1145/3600006.3613165
UR  - https://arxiv.org/abs/2309.06180
ER  - 


TY  - CONF
ID  - cs-19-2
TI  - FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
AU  - Dao, Tri
AU  - Fu, Daniel Y.
AU  - Ermon, Stefano
AU  - Rudra, Atri
AU  - Re, Christopher
T2  - Advances in Neural Information Processing Systems 35
PY  - 2022
UR  - https://arxiv.org/abs/2205.14135
ER  - 


TY  - CONF
ID  - cs-19-3
TI  - Orca: A Distributed Serving System for Transformer-Based Generative Models
AU  - Yu, Gyeong-In
AU  - Jeong, Joo Seong
AU  - Kim, Geon-Woo
AU  - Kim, Soojeong
AU  - Chun, Byung-Gon
T2  - USENIX OSDI
PY  - 2022
UR  - https://www.usenix.org/conference/osdi22/presentation/yu
ER  -