Autograd Python Packages

torch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

autograd-gamma

NotImplementedError: VJP of gammainc wrt argnum 0 not defined

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.

torch-sparse

PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations

lucid-dl

Lumerico's Comprehensive Interface for Deep Learning

datarax

A Differentiable Data Pipeline Framework for JAX

neuralengine

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

pyerrors

Error propagation and statistical analysis for Monte Carlo simulations in lattice QCD and statistical mechanics using autograd.

agent-torch

large population models

mygrad

Drop-in autodiff for NumPy.

norse

A library for deep learning with spiking neural networks

boost-loss

Utilities for easy use of custom losses in CatBoost, LightGBM, XGBoost

nabla-ml

Nabla: High-Performance Scientific Computing

nets

Recreating PyTorch from scratch, using Numpy. Supports FCN, CNN, RNN layers.

torch-yottaxx

Autograd Library,which seems like a simple torch.For deep-learning study,it can implement simple neural networks.

pyember

ML Library from scratch with only standard libraries

nnetflow

A minimal neural network framework with autodiff and NumPy

legume-gme

🌱 Guided-mode expansion of photonic crystal slabs

loupe

Parametric optimization with built-in autograd

neuralforge

An educational framework similar to PyTorch, built to be interpretable and easy to implement.

torchvine

Pure-PyTorch vine copula modelling — GPU-ready, differentiable, and API-compatible with pyvinecopulib

vistan

Library to run VI algorithms on Stan models.

pydynet

NumPy-based Dynamic Deep Learning Framework

essos

e-Stellarator Simulation and Optimization Suite