thustorage/GustANN

High-Throughput, Cost-Effective Billion-Scale Vector Search with a Single GPU [to appear in SIGMOD'26]

38
/ 100
Emerging

GustANN helps data scientists and machine learning engineers quickly find the most similar items (vectors) among billions of possibilities. You provide a dataset of numerical vectors and a query vector, and it efficiently returns the top 'k' most similar vectors, even with massive datasets that don't fit into GPU memory. This is ideal for applications requiring ultra-fast, large-scale similarity searches.

Use this if you need to perform high-throughput, billion-scale similarity searches on vector datasets with a single GPU, where the dataset is too large to fit entirely in GPU memory.

Not ideal if your datasets are small, you don't have access to high-end GPU and SSD hardware, or you require a ready-to-use solution without significant system-level setup.

vector-search similarity-matching large-scale-data machine-learning-inference data-retrieval
No License No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 7 / 25
Community 15 / 25

How are scores calculated?

Stars

21

Forks

5

Language

Cuda

License

Category

database

Last pushed

Jan 16, 2026

Commits (30d)

0

Get this data via API

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

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