Differentiable Programming Python Packages

warp-lang

A Python framework for GPU-accelerated simulation, robotics, and machine learning.

jaxopt

Hardware accelerated, batchable and differentiable optimizers in JAX.

taichi

Productive, portable, and performant GPU programming in Python.

pytorch-kinematics

Robot kinematics implemented in pytorch

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

optiland

Comprehensive optical design, optimization, and analysis in Python, including GPU-accelerated and differentiable ray tracing via PyTorch.

tesseract-jax

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

s2fft

S2FFT: Differentiable and accelerated spherical transforms

memo-lang

A probabilistic programming language for metacognitive modeling

torch-fem

GPU accelerated differentiable finite elements for solid mechanics with PyTorch

taichi-nightly

Productive, portable, and performant GPU programming in Python.

nutens

Tensor based engine for calculating neutrino oscillation probabilities in a fast, flexible, and differentiable way

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

mcfit

multiplicatively convolutional fast integral transforms, implementing FFTLog

differometor

A Differentiable Interferometer Simulator for the Computational Design of Gravitational Wave Detectors

torchbearer

torchbearer: A model fitting library for PyTorch

neuralogic

PyNeuraLogic lets you use Python to create Differentiable Logic Programs

flagquantum

Sharded, differentiable quantum simulation and training in PyTorch, reaching domestic accelerators through FlagOS.

softtorch

A library for soft differentiable relaxations of common PyTorch functions.

torch-sla

torch sparse linear algebra library

dsgp4

dSGP4: differentiable SGP4. Supports differentiability, ML integration & embarassingly parallel computations

torchtomo

Differentiable 2D CT in PyTorch with parallel/fan-beam projectors, exact adjoints, filtered backprojection, learnable scan geometry, and optional CUDA acceleration.