What it does
PyTorch is a Python library for building neural networks, the layered math systems behind most modern AI. It handles the heavy number-crunching and can use graphics cards (GPUs) to make it much faster.
Its makers say it is designed to feel natural to Python users and to let researchers change how a model behaves on the fly, which makes experimenting easier.
It is mainly used as a research platform for deep learning and as a faster, GPU-powered alternative to everyday math libraries.
Who it's for
AI researchers, students and programmers who build or train their own models.
Can I use it without coding?
Developers only. It's a code library; install commands are listed on the PyTorch website. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Linux, Windows, Mac
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page or the official download page above. Copies with similar names exist for many popular projects.
- No standard license listed. Check the GitHub page before using it for business.
- More on staying safe
Where people are talking about it
- PyTorch 1.8, with AMD ROCm supportHacker News · Mar 2021
- PyTorch 1.0 is outHacker News · Dec 2018