Optimum

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

Overview

🤗 Optimum provides an integration with Torch FX, a library for PyTorch that allows developers to implement custom transformations of their models that can be optimized for performance.

How-to guides

Practical guides to help you achieve a specific goal. Take a look at these guides to learn how to use 🤗 Optimum to solve real-world problems.

Conceptual guides

High-level explanations for building a better understanding about important topics such as quantization and graph optimization.

Reference

Technical descriptions of how the Torch FX classes and methods of 🤗 Optimum work.

< > Update on GitHub

←How to add support for new architectures? Optimization→