pyg-team / pyg-lib

Low-Level Graph Neural Network Operators for PyG

224 stars

58 forks

28 issues

Chat with Codebase Architecture Scan Security Audit Explain Codebase

AI Architecture Analysis

This repository is indexed by RepoMind. By analyzing pyg-team/pyg-lib in our AI interface, you can instantly generate complete architecture diagrams, visualize control flows, and perform automated security audits across the entire codebase.

Our Agentic Context Augmented Generation (Agentic CAG) engine loads full source files into context on-demand, avoiding the fragmentation of traditional RAG systems. Ask questions about the architecture, dependencies, or specific features to see it in action.

Source files are only loaded when you start an analysis to optimize performance.

Click here to launch the interactive analysis workspace

Embed this Badge

Showcase RepoMind's analysis directly in your repository's README.

[![Analyzed by RepoMind](https://img.shields.io/badge/Analyzed%20by-RepoMind-4F46E5?style=for-the-badge)](https://repomind.in/repo/pyg-team/pyg-lib)

Preview:

Repository Overview (README excerpt)

Crawler view

[contributing-image]: https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat&color=4B26A4 [contributing-url]: https://github.com/pyg-team/pytorch_geometric/blob/master/.github/CONTRIBUTING.md [coverage-image]: https://codecov.io/gh/pyg-team/pyg-lib/branch/master/graph/badge.svg [coverage-url]: https://codecov.io/github/pyg-team/pyg-lib?branch=master [docs-image]: https://readthedocs.org/projects/pyg-lib/badge/?version=latest [docs-url]: https://pyg-lib.readthedocs.io/en/latest/?badge=latest [slack-image]: https://img.shields.io/badge/slack-join-white.svg?logo=slack&color=4B26A4 [slack-url]: https://data.pyg.org/slack.html pyg-lib [![Docs Status][docs-image]][docs-url] [![Code Coverage][coverage-image]][coverage-url] [![Slack][slack-image]][slack-url] [![Contributing][contributing-image]][contributing-url] Installation We provide pre-built Python wheels for all major OS/PyTorch/CUDA combinations from Python 3.10 till 3.13, see here. To install the wheels, simply run where • should be replaced by either , , or • should be replaced by either , , , , or The following combinations are supported: | PyTorch 2.10 | | | | | | |--------------|-------|---------|---------|---------|---------| | **Linux** | ✅ | ✅ | ✅ | | ✅ | | **Windows** | ✅ | ✅ | ✅ | | ✅ | | **macOS** | ✅ | | | | | | PyTorch 2.9 | | | | | | |--------------|-------|---------|---------|---------|---------| | **Linux** | ✅ | ✅ | ✅ | | ✅ | | **Windows** | ✅ | ✅ | ✅ | | ✅ | | **macOS** | ✅ | | | | | | PyTorch 2.8 | | | | | | |--------------|-------|---------|---------|---------|---------| | **Linux** | ✅ | ✅ | ✅ | ✅ | | | **Windows** | ✅ | ✅ | ✅ | ✅ | | | **macOS** | ✅ | | | | | From nightly Nightly wheels are provided for Linux from Python 3.10 till 3.13: From master