USENIX supports diversity, equity, and inclusion and condemns hate and discrimination.
DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving
Submitted by admin on May 9, 2024 - 4:00 pm
| Title | DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving |
| Publication Type | Conference Paper |
| Year of Publication | 2024 |
| Authors | Zhong Y, Liu S, Chen J, Hu J, Zhu Y, Liu X, Jin X, Zhang H |
| Conference Name | 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24) |
| Date Published | 07/2024 |
| Publisher | USENIX Association |
| Conference Location | Santa Clara, CA |
| ISBN Number | 978-1-939133-40-3 |
| URL | https://www.usenix.org/conference/osdi24/presentation/zhong-yinmin |