# patrick-kidger/diffrax

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

Repository: https://github.com/patrick-kidger/diffrax
Canonical: https://ross.abutalabs.com/products/diffrax
Language: Python
License: Apache-2.0
License Family: permissive
Topics: differential-equations, jax, deep-learning, neural-differential-equations, machine-learning, dynamical-systems, neural-networks, equinox
Last push: 2026-06-21T10:38:03+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 88, release rhythm 59, longevity 100
- inputs: {"age_days": 1865, "days_push": 73, "days_rel": 197, "gap_med": 47.5, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2089, forks 186 (observed 2026-08-28T04:06:12.260731+00:00)

## What it is
Diffrax is a JAX-based library providing numerical differential equation solvers for ODEs, SDEs, and CDEs. It is fully autodifferentiable and GPU-capable, with support for neural differential equations and multiple adjoint methods for backpropagation.

## Use cases
- solve ODEs in JAX with GPU acceleration
- train neural differential equations with backpropagation
- simulate stochastic differential equations differentiably
- integrate controlled differential equations for time series models
- run differentiable physics or dynamical systems simulations
- vmapped batch integration of differential equations

## When to choose
- you need differentiable, GPU-capable ODE/SDE/CDE solvers within the JAX ecosystem
- you are training neural differential equations or scientific ML models
- you want many solver choices (Tsit5, Dopri8, symplectic, implicit) in one unified library

## When to avoid
- you work outside the JAX/Python ecosystem
- you need a general-purpose non-differentiable solver without GPU requirements
- you need symbolic or exact analytical solutions rather than numerical integration

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, simulation, math, gpu-computing
- domain: machine-learning, deep-learning, data-science
- platform: python, cross-platform
- tags: jax, differential-equations, ode, sde, cde, neural-differential-equations, numerical-solvers, autodiff, scientific-computing, dynamical-systems, algorithms, gpu

## Member repositories
- patrick-kidger/diffrax (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:12.260731+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:55:39.569734+00:00, confidence not recorded.
  - readme: https://github.com/patrick-kidger/diffrax (fetched 2026-08-28T04:06:12.260731+00:00, sha 3d6b94316bf1)
  - registry_pypi: https://pypi.org/pypi/diffrax/json (fetched 2026-08-29T10:35:27.063076+00:00, sha e25d04182999)
- Data as of 2026-08-30T08:39:29.467469+00:00.