Automatic Differentiation Python Packages

pin

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

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.

libpinocchio

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

tensorcircuit-nightly

The next-gen AI-native tensor-network-based quantum software framework

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.

ott-jax

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

aesara

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

aesara-nightly

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

pennylane-catalyst

A JIT compiler for hybrid quantum programs in PennyLane

neurograd

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

tesseract-core

Universal components for differentiable scientific computing. :package:

torchopt

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

tad-mctc

PyTorch Automatic Differentiation Utility for "tad" Projects.

jaxsim

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

tad-dftd3

PyTorch Autodiff DFT-D3 Implementation.

varipeps

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

tensortrax

Differentiable Tensors based on NumPy Arrays

sll-core

SLL-Core: PyTorch library for automatic differentiation through discrete operations via Static Local Linearization.

nextstat

Universal differentiable statistical inference engine (Rust + GPU). High-performance Frequentist & Bayesian modeling, RL environments, and end-to-end optimization for Science, Pharma, and Finance

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

nanograd-bgriebel

Scalar automatic differentiation engine.

adam-robotics

adam implements a collection of algorithms for calculating rigid-body dynamics in Jax, CasADi, PyTorch, and Numpy.