Equinox
JAX neural network library with PyTorch-like module system.
About
Equinox by Patrick Kidger is a neural network library for JAX that represents models as PyTrees of plain Python classes, giving a PyTorch-like module system without leaving the JAX ecosystem. Filtered transformations let parameters and static fields coexist while passing cleanly through JIT and gradient boundaries, and it adds features like runtime error handling and PyTree manipulation. It underpins libraries such as Diffrax. Released under the Apache 2.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- AI Frameworks & Libraries
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Advanced (4/5)
- License
- Apache-2.0
- Added
- Apr 3, 2026
Related Tools
Unified system for large-scale distributed training and inference.
Guidance language for controlling LLM generation with constraints, grammars, and JSON schemas.
Library for easily accessing and processing ML datasets.
High-level deep learning API supporting JAX, TensorFlow, and PyTorch backends.
Neural network library for JAX by Google providing Linen module system.
Gradient boosting library by Yandex with native categorical feature handling.