
torchdyn
by DiffEqML (organization)
A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods (description from the project’s GitHub page)
Repository facts
- Stars
- 1,581
- Forks
- 135
- Open issues and pull requests
- 40
- Primary language
- Jupyter Notebook
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- DiffEqML · Organization
- Created
- Apr 27, 2020
- Last push
- May 2, 2024
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 3,499: patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
2,114 starsPythonApache-2.0Last push Sep 6, 2026
Rank 6,399: SciML/DiffEqFlux.jl
Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine lea…
929 starsJuliaMITLast push Oct 18, 2026
Rank 2,483: SciML/DifferentialEquations.jl
Multi-language suite for high-performance solvers of differential equations and scientific machine learning (SciML) components. Ordinary differential equations (ODEs), stochastic…
3,167 starsJuliaOther licenseLast push Oct 17, 2026
Rank 5,286: SciML/NeuralPDE.jl
Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
1,235 starsJuliaOther licenseLast push Oct 17, 2026
Rank 5,902: raminmh/CfC
Closed-form Continuous-time Neural Networks
1,056 starsPythonApache-2.0Last push Jul 5, 2024
Rank 4,870: pnnl/neuromancer
Pytorch-based framework for solving parametric constrained optimization problems, physics-informed system identification, and parametric model predictive control.
1,383 starsPythonOther licenseLast push Oct 7, 2026