patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
This is a tool for scientists and engineers who need to simulate complex systems over time using differential equations. It takes your system's equations and initial conditions, then precisely calculates how the system evolves. Researchers in fields like physics, biology, and finance can use this to model dynamic processes.
1,930 stars. Used by 6 other packages. Actively maintained with 1 commit in the last 30 days. Available on PyPI.
Use this if you need to accurately solve ordinary, stochastic, or controlled differential equations and require automatic differentiation for analysis or optimization, especially for large-scale models or neural differential equations.
Not ideal if you're not comfortable with programming in Python and JAX, or if your problem doesn't involve differential equations.
Stars
1,930
Forks
175
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 23, 2026
Commits (30d)
1
Dependencies
7
Reverse dependents
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/patrick-kidger/diffrax"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
explosion/thinc
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
google-deepmind/optax
Optax is a gradient processing and optimization library for JAX.
google/grain
Library for reading and processing ML training data.
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
extropic-ai/thrml
Thermodynamic Hypergraphical Model Library in JAX