Parrot: Efficient Serving of LLM-based Applications with Semantic Variable
Chaofan Lin, Zhenhua Han*, Chengruidong Zhang, Yuqing Yang*, Fan Yang, Chen Chen*, Lili Qiu
(* Corresponding author)
18th USENIX Symposium on Operating Systems Design and Implementation (OSDI'24)
[arXiv] |
[code]
|
[conference page]