# What is PyTorch? Definition and meaning

A flexible framework with dynamic computation graphs and strong GPU support.

## Definition

**PyTorch**: A flexible framework with dynamic computation graphs and strong GPU support.

In short: Deep-learning framework.

## When it is used

The main framework for research and production models.

## Where it fits

PyTorch belongs to **Frameworks** in the [Deep learning](/topics/deep-learning) topic. These are the other terms in the same group:

- **[PyTorch Lightning](/glossary/pytorch-lightning)**: A library that organizes training loops, distributed training and logging.
- **[TensorFlow](/glossary/tensorflow)**: An end-to-end platform with a graph runtime and deployment tooling.
- **[Keras](/glossary/keras)**: A simple API for defining and training neural networks across several backends.
- **[JAX](/glossary/jax)**: A library for array computing with automatic differentiation, JIT compilation and easy parallelism on accelerators.
- **[Hugging Face](/glossary/hugging-face)**: A platform and set of libraries for models, datasets and training tools such as Transformers.

## Learn more

The full guide to **[PyTorch](/tools/pytorch)** explains how it works, when to use it and how it compares with the alternatives, with examples. The [glossary](/glossary) lists every term on the site from A to Z.

Previous term: [PySpark](/glossary/pyspark) · Next term: [PyTorch Lightning](/glossary/pytorch-lightning)
