# NVIDIA cuVS

> NVIDIA cuVS is a GPU-accelerated approximate nearest neighbor search library utilizing CUDA for high-performance CAGRA, HNSW, IVF-PQ indexes on billion-scale datasets. Supports batch queries for high-throughput operations, ideal for large-scale similarity search and real-time recommendations. Delivers up to 12x faster index building and 8x lower query latency compared to CPU-only implementations like Milvus.

- **URL:** https://rapids.ai/cuvs/
- **Category:** GPU Accelerated Vector DBs
- **Tags:** Gpu Acceleration, Cuda, Gpu Support
- **Featured:** yes
- **Updated:** 2026-04-23 19:19
- **Canonical page:** https://vectordb.ever.works/items/nvidia-cuvs

## Details

## Overview

cuVS is a GPU-accelerated library for vector search and clustering from NVIDIA RAPIDS. Enables databases to scale up and out for massive-scale vector search workloads, delivering unmatched speed through GPU acceleration.

## Performance Benefits

### Index Building
- **12x faster** index building on GPU at 95% recall (vs. CPU)
- Massive speedups for large datasets
- Parallel processing on GPU architecture

### Query Performance
- **8x lower** search latencies at 95% recall
- Higher throughput at all recall levels
- Better latency characteristics

## Supported Algorithms

- **IVF-PQ**: Inverted File with Product Quantization
- **IVF-Flat**: Inverted File with flat vectors
- **CAGRA**: CUDA-Accelerated Graph-based ANN
- **HNSW**: Hierarchical Navigable Small World
- **Brute Force**: Exact search option

## Pricing

Free and open-source under Apache 2.0 license.

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://vectordb.ever.works/items/nvidia-cuvs._