@article{dsserveaframeworkforefficientandscalable, title = {DS SERVE: A Framework for Efficient and Scalable Neural Retrieval}, author = {Jinjian Liu and Yichuan Wang and Xinxi Lyu and Rulin Shao and Joseph E. Gonzalez and Matei Zaharia and Sewon Min}, year = {2025}, eprint = {2602.22224}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.22224}, }