← Discover
Discover · GitHub · Pytorch↑ +65 today

Flexible and fast artificial intelligence library

PyTorch is a machine learning library that offers powerful graphics processing unit (GPU) acceleration for Python-based tensor calculations and dynamic neural networks. It provides broad ecosystem support in the development and deployment of deep learning models.

Updates

  • September 3, 2026: Stars 102,131 → 102,730, latest release v2.14.0 (September 2, 2026).
  • August 2, 2026: Stars 101,297 → 102,131, latest release v2.13.0 (July 8, 2026).

What you get

  • GPU powered high performance tensor calculations
  • Flexible model development with dynamic neural networks
  • Fully compatible with the Python ecosystem

Installation

Download source code
git clone https://github.com/pytorch/pytorch
cd pytorch
# if you are updating an existing checkout
git submodule sync
git submodule update --init --recursive
Installing dependencies
pip install --group dev

If you don't write code

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to develop deep learning models using the PyTorch library. Walk me through tensor calculations, creating dynamic neural networks, and leveraging GPU acceleration. In particular, explain how to use the torch.nn and torch.autograd components, how to integrate them with the Python structure, and how to optimize the model training processes.

Related dictionary terms

Who it is forIt is suitable for researchers and software developers who want to develop deep learning models.

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-07-03: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.