patrick-kidger / diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
Why this job: topics: neural-networks, jax, deep-learning, machine-learning
What it does
Diffrax is a JAX-based library providing numerical differential equation solvers.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 months ago
- Stars
- 2,123
- +3 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.7.2
- Released 8 months ago
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 55% closed
- 226 still open
- Pull requests
- 200 merged
- 44 waiting
- Releases
- 21
- 2 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| keras-team / keras | 64,420 | today | Apache-2.0 | No downloads |
| SciML / NeuralPDE.jl | 1,238 | 9 days ago | Custom | No downloads |
| google-deepmind / dm-haiku | 3,301 | 16 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- differential-equations
- jax
- deep-learning
- neural-differential-equations
- machine-learning
- dynamical-systems
- neural-networks
- equinox
Project record
- JobAI libraries and models
- StatusListed
- Commits730
- Forks204
- Watching19
- Stars in 28 days+11
- CreatedJul 25, 2021
- First seen by usNov 7, 2026
- CheckedNov 8, 2026