DS SERVE: A Framework for Efficient and Scalable Neural Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912927462719488 |
|---|---|
| author | Liu, Jinjian Wang, Yichuan Lyu, Xinxi Shao, Rulin Gonzalez, Joseph E. Zaharia, Matei Min, Sewon |
| author_facet | Liu, Jinjian Wang, Yichuan Lyu, Xinxi Shao, Rulin Gonzalez, Joseph E. Zaharia, Matei Min, Sewon |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22224 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DS SERVE: A Framework for Efficient and Scalable Neural Retrieval Liu, Jinjian Wang, Yichuan Lyu, Xinxi Shao, Rulin Gonzalez, Joseph E. Zaharia, Matei Min, Sewon Information Retrieval Artificial Intelligence Computation and Language 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. |
| title | DS SERVE: A Framework for Efficient and Scalable Neural Retrieval |
| topic | Information Retrieval Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2602.22224 |