rapidsai/cuvs
cuVS - a library for vector search and clustering on the GPU
Implements approximate nearest neighbors (ANN) and clustering algorithms optimized for NVIDIA GPUs, built on the RAPIDS RAFT library for high-performance ML primitives. Supports multiple language bindings (Python, C++, C, Rust) and integrates with downstream databases and ML frameworks for semantic search, RAG, and graph construction. Features state-of-the-art algorithms like CAGRA for index building and search with automatic optimization across CUDA versions and GPU architectures.
646 stars. Actively maintained with 69 commits in the last 30 days.
Stars
646
Forks
164
Language
Cuda
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
69
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/rapidsai/cuvs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.