arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.22224cs.IRcs.AIcs.CL
收藏

DS SERVE:一种高效可扩展的神经检索框架

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

AI总结:

DS-SERVE是一种高效可扩展的神经检索框架,通过低延迟和内存优化支持多种大规模应用

摘要:

我们介绍了DS-Serve,一种将包含半万亿个标记的大型文本数据集转换为高性能神经检索系统的框架。DS-Serve提供了网页界面和API端点,能够在单个节点上实现低延迟并具有适度的内存开销。该框架还支持推理时在延迟、准确性和结果多样性之间的权衡。我们预计DS-Serve将在大规模检索增强生成(RAG)、训练数据归因、训练搜索代理等多个应用中得到广泛应用。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑