Parrot: Efficient Serving of LLM-based Applications with Semantic Variable

TitleParrot: Efficient Serving of LLM-based Applications with Semantic Variable
Publication TypeConference Paper
Year of Publication2024
AuthorsLin C, Han Z, Zhang C, Yang Y, Yang F, Chen C, Qiu L
Conference Name18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)
Date Published07/2024
PublisherUSENIX Association
Conference LocationSanta Clara, CA
ISBN Number978-1-939133-40-3
URLhttps://www.usenix.org/conference/osdi24/presentation/lin-chaofan