cgtuebingen/ggnn

GGNN: State of the Art Graph-based GPU Nearest Neighbor Search

44
/ 100
Emerging

Builds approximate nearest-neighbor search graphs on CUDA GPUs using a graph-based traversal algorithm, scaling to billion-scale datasets across multiple GPUs via sharding. Supports zero-copy data exchange with PyTorch tensors and numpy arrays, and exposes both C++20/CUDA and Python APIs with configurable distance measures (Euclidean, cosine) and tunable search parameters for accuracy-speed tradeoffs.

170 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

170

Forks

27

Language

Cuda

License

Apache-2.0

Last pushed

Feb 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/cgtuebingen/ggnn"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.