sashakolpakov/dire-jax
DImensionality REduction in JAX
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.
Stars
26
Forks
4
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
cosmosgl/graph
GPU-accelerated force graph layout and rendering
Clay-foundation/model
The Clay Foundation Model - An open source AI model and interface for Earth
nomic-ai/nomic
Nomic Developer API SDK
alexshtf/torchcurves
Parametric differentiable curves with PyTorch for continuous embeddings, shape-restricted models, or KANs
omoindrot/tensorflow-triplet-loss
Implementation of triplet loss in TensorFlow