---
id: cuvs-cu12
version: "26.8.1"
license: Apache-2.0
license_treatment: permissive
maintenance: active
---

# cuvs-cu12 — cuVS: Vector Search on the GPU

License: permissive · Maintenance: active · Downloads: 115.5K/mo

## What it is and what it does

cuVS is a GPU-accelerated library for vector search and clustering built on NVIDIA's RAPIDS RAFT primitives. It implements algorithms like CAGRA for approximate nearest neighbor search, enabling fast similarity queries on embedding collections. The library is designed to accelerate semantic search, recommendation systems, and clustering workloads by offloading computation to NVIDIA GPUs.

The package provides Python, C++, C, and Rust APIs. It depends on libcuvs-cu12 (the core CUDA library), pylibraft-cu12 (RAPIDS RAFT bindings), cuda-bindings, and numpy. Installation requires Python 3.11 or later and a compatible NVIDIA GPU with CUDA 12 support. The library is actively maintained and handles CUDA version compatibility automatically.

Use it for:

- Build semantic search systems for retrieval-augmented generation (RAG) pipelines using GPU acceleration
- Implement GPU-accelerated k-nearest neighbor graph construction for clustering and visualization algorithms
- Deploy high-throughput embedding similarity search in recommendation systems or image/text search applications
- Accelerate data mining tasks like clustering and visualization by computing nearest neighbor graphs on GPU
- Integrate vector search into databases or applications that need low-latency similarity queries at scale

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Provides GPU-accelerated approximate nearest neighbor search and clustering algorithms optimized for NVIDIA GPUs.

Yes, if you have NVIDIA GPU hardware and need fast vector search or clustering. The active maintenance, permissive Apache-2.0 license, and zero known vulnerabilities make it production-ready. Medium install friction (CUDA dependencies) is the main trade-off; ensure your environment has compatible NVIDIA hardware and CUDA 12 support before installing.

## Install

pip install cuvs-cu12
uv add cuvs-cu12
poetry add cuvs-cu12

## Installing cuvs-cu12

Before you install: Medium install friction due to CUDA 12 GPU library dependencies (libcuvs-cu12, pylibraft-cu12, cuda-bindings, numpy). Active maintenance with recent releases.

License in practice: Apache-2.0 permissive license allows commercial and private use with minimal restrictions, making it suitable for production applications.

Quickstart:

pip install cuvs-cu12

from cuvs.neighbors import cagra

index_params = cagra.IndexParams()
index = cagra.build(index_params, dataset)

Requires NVIDIA GPU with CUDA 12 support and compatible CUDA runtime environment installed on the system.

Verify before relying:

- Whether the package works on non-NVIDIA GPUs or requires NVIDIA-specific hardware
- Performance characteristics compared to CPU-based vector search libraries
- Specific NVIDIA GPU compute capability requirements beyond CUDA 12
- Typical dataset and query sizes the library is optimized for

## Package facts

- License: Apache-2.0 (permissive)
- Python support: supports_current
- Install friction: medium
- Maintenance: active
- Downloads: 115.5K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

GPU vector search, nearest neighbor search GPU, vector similarity clustering, approximate nearest neighbors, CUDA vector indexing, semantic search GPU, embedding search acceleration, gpu-accelerated, vector-search, rapids

[View on SkillFed](https://skillfed.io/packages/cuvs-cu12) · [View on PyPI](https://pypi.org/project/cuvs-cu12/)