sashakolpakov/dire-jax

DImensionality REduction in JAX

48
/ 100
Emerging

Implements global structure-preserving dimensionality reduction through homological stability guarantees, with fully vectorized JIT-compiled computation and mixed-precision arithmetic support. Integrates with JAX's CPU/GPU acceleration backend and provides memory-efficient chunking for datasets up to 100K+ points, competing with UMAP and t-SNE while offering optimized kernel caching and automatic large-dataset mode management.

Available on PyPI.

Maintenance 6 / 25
Adoption 11 / 25
Maturity 18 / 25
Community 13 / 25

How are scores calculated?

Stars

26

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Nov 21, 2025

Monthly downloads

34

Commits (30d)

0

Dependencies

9

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/sashakolpakov/dire-jax"

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