DS SERVE: A Framework for Efficient and Scalable Neural Retrieval
Jinjian Liu
Yichuan Wang
Xinxi Lyu
Rulin Shao
Joseph E. Gonzalez
Matei Zaharia
Sewon Min
- AI4TS3DV
Main:2 Pages
1 Figures
Bibliography:1 Pages
1 Tables
Abstract
We present DS-Serve, a framework that transforms large-scale text datasets, comprising half a trillion tokens, into a high-performance neural retrieval system. DS-Serve offers both a web interface and API endpoints, achieving low latency with modest memory overhead on a single node. The framework also supports inference-time trade-offs between latency, accuracy, and result diversity. We anticipate that DS-Serve will be broadly useful for a range of applications, including large-scale retrieval-augmented generation (RAG), training data attribution, training search agents, and beyond.
View on arXivComments on this paper
