Automatic Differentiation Python Packages

autograd

Efficiently computes derivatives of NumPy code.

pin

A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives

libpinocchio

A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives

aerosandbox

Aircraft design optimization made fast through computational graph transformations (e.g., automatic differentiation). Composable analysis tools for aerodynamics, propulsion, structures, trajectory design, and much more.

pennylane

PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.

aesara

Aesara is a Python library for defining, optimizing, and efficiently evaluating mathematical expressions involving multi-dimensional arrays.

ott-jax

Optimal transport tools implemented with the JAX framework, to solve large scale matching problems of any flavor.

tesseract-core

Universal components for differentiable scientific computing. :package:

torchopt

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

advect

Automatic differentiation for the NumPy code you already write

aesara-nightly

Aesara is a Python library for defining, optimizing, and efficiently evaluating mathematical expressions involving multi-dimensional arrays.

jaxsim

A differentiable physics engine and multibody dynamics library for control and robot learning.

pennylane-catalyst

A JIT compiler for hybrid quantum programs in PennyLane

treams-rs

A Rust port of treams with a Python interface and analytic gradients.

tesseract-jax

Execute + differentiate Tesseracts as part of JAX programs, with full support for function transformations like JIT, grad, and more. ⚡

neurograd

A Pure Python Deep Learning Framework with Automatic Differentiation and PyTorch-like API

tad-mctc

PyTorch Automatic Differentiation Utility for "tad" Projects.

varipeps

variPEPS -- Versatile tensor network library for variational ground state simulations in two spatial dimensions

tensortrax

Differentiable Tensors based on NumPy Arrays

asdex

Automatic Sparse Differentiation in JAX.

tad-dftd3

PyTorch Autodiff DFT-D3 Implementation.

tad-multicharge

PyTorch Autodiff Multicharge (Classical Charge Models).

neuralengine

An open-source framework/library for building and training neural networks in Python with support for GPUs (CUDA).

hyperjet

Algorithmic differentiation with hyper-dual numbers in C++ and Python