Optimum

Overview

🤗 Optimum Installation Quick tour Notebooks

Conceptual guides

Quantization

Nvidia

AMD

Intel

AWS Trainium/Inferentia

Google TPUs

for Intel Gaudi

ExecuTorch

Furiosa

ONNX Runtime

Exporters

Overview The TasksManager

ONNX

TFLite

BetterTransformer

Torch FX

LLM quantization

Utilities

You are viewing v1.26.0 version. A newer version v1.26.1 is available.

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 enables exporting models from PyTorch or TensorFlow to different formats through its exporters module. For now, three exporting format are supported: ONNX and TFLite (TensorFlow Lite).

< > Update on GitHub

←Trainer The TasksManager→