VecFlow: A High-Performance Vector Data Management System for Filtered-Search on GPUs
Jingyi Xi, Chenghao Mo, Benjamin Karsin, Artem Chirkin, Mingqin Li, Minjia Zhang

TL;DR
VecFlow is a GPU-optimized vector search system that significantly outperforms CPU-based solutions in throughput and recall, enabling efficient filtered-ANNS for AI applications.
Contribution
The paper introduces VecFlow, a novel GPU-based vector filtered search system with a label-centric index and architecture-aware optimizations, achieving high throughput and recall.
Findings
Achieves 5 million QPS at 90% recall on NVIDIA A100 GPU.
Outperforms CPU solutions like Filtered-DiskANN by up to 135 times.
Supports high recall (99%) with better scalability than existing GPU baselines.
Abstract
Vector search and database systems have become a keystone component in many AI applications. While many prior research has investigated how to accelerate the performance of generic vector search, emerging AI applications require running more sophisticated vector queries efficiently, such as vector search with attribute filters. Unfortunately, recent filtered-ANNS solutions are primarily designed for CPUs, with few exploration and limited performance of filtered-ANNS that take advantage of the massive parallelism offered by GPUs. In this paper, we present VecFlow, a novel high-performance vector filtered search system that achieves unprecedented high throughput and recall while obtaining low latency for filtered-ANNS on GPUs. We propose a novel label-centric indexing and search algorithm that significantly improves the selectivity of ANNS with filters. In addition to algorithmic level…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Database Systems and Queries · Data Stream Mining Techniques · Data Management and Algorithms
