autograd

Automate gameplay for Get Strong For Brainrots on Windows with speed and aim assistance tools.

Differentiable option pricing and volatility surfaces in PyTorch — Heston, Bates, Merton, Variance Gamma via Fourier-COS; SVI/SABR surfaces; rough Bergomi. Greeks from autograd, calibration by gradient descent.

Reproduce Embedded Language Flows using PyTorch. This implementation provides access to ELF models trained on OpenWebText.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

🧠 Visualize neural network architectures interactively to enhance your understanding of deep learning, from basic perceptrons to advanced transformers.

A TypeScript implementation of an autograd engine for educational purposes.

Guards two real PyTorch bugs: nested-JVP slogdet silent zero (pytorch#196697) and jagged narrow+unbind element-selection error (pytorch#196708)

A from-scratch deep learning framework with automatic differentiation, GPU support, and neural network modules. 8,000+ lines of pure Python — like micro-PyTorch, built for understanding.

The public trace of a roadmap toward ML systems: a Python socle, a GPT trained from a blank file, then C, CUDA and a contribution to an inference engine. Every check can fail, and each one was broken on purpose first.

A tiny neural-network framework in pure Go with AVX2 SIMD kernels (GOEXPERIMENT=simd)

Lumerico's Comprehensive Interface for Deep Learning

Eiko: the GPU-accelerated Eikonal equation solver

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

Create procedural 2D avatars in your browser with SVG rendering, expressions, animations, and JSON export—no backend needed.

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.

A reverse-mode automatic differentiation engine built from scratch in Python — no PyTorch, no TensorFlow. 97.63% on MNIST, 737 tests, 183 gradient checks, and 21 chapters explaining every derivative.

Pure C# N-dimensional strided tensor engine and zero-allocation autograd framework for .NET 10. Native alternative to TensorFlow and PyTorch.

Explore quantum computing with notebooks, guides, and code for core concepts, algorithms, and hands-on learning

Introductions to key concepts in quantum programming, as well as tutorials and implementations from cutting-edge quantum computing research.

The Machinery Behind Machine Learning.