# What is TensorFlow? Definition and meaning

An end-to-end platform with a graph runtime and deployment tooling.

## Definition

**TensorFlow**: An end-to-end platform with a graph runtime and deployment tooling.

In short: Google's machine-learning platform.

## When it is used

Production deployments, mobile and TPU workloads.

## Where it fits

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

- **[PyTorch](/glossary/pytorch)**: A flexible framework with dynamic computation graphs and strong GPU support.
- **[PyTorch Lightning](/glossary/pytorch-lightning)**: A library that organizes training loops, distributed training and logging.
- **[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 **[TensorFlow](/tools/tensorflow)** 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: [Tensor parallelism](/glossary/tensor-parallelism) · Next term: [TensorRT](/glossary/tensorrt)
