#206206th of 242 in ML frameworks and libraries

diffrax

JAX library of ODE, SDE and CDE solvers with autodiff

Stars
2.1k
License
Apache-2.0
Last commit
Sep 2026
Last release
Feb 2026
Language
Python
Stars, last 29 weeks+147
25 Apr 2026: 1,982 stars2 May 2026: 1,988 stars9 May 2026: 1,993 stars16 May 2026: 2,001 stars23 May 2026: 2,005 stars30 May 2026: 2,021 stars6 Jun 2026: 2,033 stars13 Jun 2026: 2,043 stars20 Jun 2026: 2,049 stars27 Jun 2026: 2,056 stars4 Jul 2026: 2,058 stars11 Jul 2026: 2,064 stars18 Jul 2026: 2,066 stars25 Jul 2026: 2,074 stars1 Aug 2026: 2,078 stars8 Aug 2026: 2,082 stars15 Aug 2026: 2,084 stars22 Aug 2026: 2,087 stars29 Aug 2026: 2,091 stars5 Sept 2026: 2,092 stars12 Sept 2026: 2,097 stars19 Sept 2026: 2,104 stars26 Sept 2026: 2,106 stars3 Oct 2026: 2,108 stars10 Oct 2026: 2,110 stars17 Oct 2026: 2,115 stars24 Oct 2026: 2,118 stars31 Oct 2026: 2,122 stars7 Nov 2026: 2,123 stars14 Nov 2026: 2,129 stars

1,982 on 25 Apr 20262,129 on 14 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

Diffrax provides numerical solvers for ordinary, stochastic and controlled differential equations in JAX. All equation types go through one interface, `diffeqsolve`. It includes explicit solvers such as Tsit5, Dopri5 and Dopri8, plus symplectic and implicit solvers, and offers several adjoint methods for backpropagation.

Who it is for: Researchers and engineers solving differential equations in JAX

Strengths

  • Single API covers ODEs, SDEs and CDEs, including neural differential equations
  • Autodifferentiable and vmappable, with multiple adjoint methods for backpropagation
  • Supports PyTrees as state and dense solutions
  • Installs with pip; hosted documentation site

Weaknesses

  • Requires JAX and Python 3.10+; not usable from other array frameworks
  • Aimed at scientific computing, not LLM or generative model workflows
  • No benchmarks against other solver libraries in the README

What it needs

  • GPU optional
  • Needs JAX, Python 3.10+

What changed

From the release notes. No flag means the note does not say so, not that the upgrade is safe.

Also in ML frameworks and libraries

See all 242
Also in ML frameworks and libraries
RankProjectScore
1transformersModel-definition library for pretrained text, vision, audio and multimodal models169.3k starsApache-2.094 out of 100
2ultralyticsPython library and CLI for training and running YOLO vision models63.5k starsAGPL-3.094 out of 100
3pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts37.3k starsApache-2.094 out of 100
#4pytorchPython tensor library with GPU support and tape-based autograd105.8k starscustom license93 out of 100
#5supervisionPython toolkit for loading, annotating and counting computer vision detections Live demo ↗ (opens in a new tab)51.7k starsMIT92 out of 100