Repository files navigation

Optimum is an extension of Transformers 🤖 Diffusers 🧨 TIMM 🖼️ and Sentence-Transformers 🤗, providing a set of optimization tools and enabling maximum efficiency to train and run models on targeted hardware, while keeping things easy to use.

Optimum can be installed usingpip as follows:

python -m pip install optimum

If you'd like to use the accelerator-specific features of Optimum, you can check the documentation and install the required dependencies according to the table below:

The--upgrade --upgrade-strategy eager option is needed to ensure the different packages are upgraded to the latest possible version.

To install from source:

python -m pip install git+https://github.com/huggingface/optimum.git

For the accelerator-specific features, appendoptimum[accelerator_type] to the above command:

python -m pip install optimum[onnxruntime]@git+https://github.com/huggingface/optimum.git

Optimum provides multiple tools to export and run optimized models on various ecosystems:

• ONNX /ONNX Runtime, one of the most popular open formats for model export, and a high-performance inference engine for deployment.
• OpenVINO, a toolkit for optimizing, quantizing and deploying deep learning models on Intel hardware.
• ExecuTorch, PyTorch’s native solution for on-device inference across mobile and edge devices.
• Intel Gaudi Accelerators enabling optimal performance on first-gen Gaudi, Gaudi2 and Gaudi3.
• AWS Inferentia for accelerated inference on Inf2 and Inf1 instances.
• NVIDIA TensorRT-LLM.

Theexport and optimizations can be done both programmatically and with a command line.

🚨🚨🚨 ONNX integration was moved tooptimum-onnx so make sure to follow the installation instructions 🚨🚨🚨

Before you begin, make sure you have all the necessary libraries installed :

pip install --upgrade --upgrade-strategy eager optimum[onnx]

It is possible to export Transformers, Diffusers, Sentence Transformers and Timm models to theONNX format and perform graph optimization as well as quantization easily.

For more information on the ONNX export, please check thedocumentation.

Once the model is exported to the ONNX format, we provide Python classes enabling you to run the exported ONNX model in a seamless manner usingONNX Runtime in the backend.

For this make sure you have ONNX Runtime installed, fore more information check out theinstallation instructions.

More details on how to run ONNX models withORTModelForXXX classeshere.

Before you begin, make sure you have all the necessarylibraries installed.

You can find more information on the different integration in ourdocumentation and in the examples ofoptimum-intel.

Before you begin, make sure you have all the necessary libraries installed :

pip install optimum-executorch@git+https://github.com/huggingface/optimum-executorch.git

Users can export Transformers models toExecuTorch and run inference on edge devices within PyTorch's ecosystem.

For more information about export Transformers to ExecuTorch, please check the doc forOptimum-ExecuTorch.

Quanto is a pytorch quantization backend which allows you to quantize a model either using the python API or theoptimum-cli.

You can see more details andexamples in theQuanto repository.

Optimum provides wrappers around the original TransformersTrainer to enable training on powerful hardware easily.We support many providers:

• Intel Gaudi Accelerators (HPU) enabling optimal performance on first-gen Gaudi, Gaudi2 and Gaudi3.
• AWS Trainium for accelerated training on Trn1 and Trn1n instances.
• ONNX Runtime (optimized for GPUs).

Before you begin, make sure you have all the necessary libraries installed :

pip install --upgrade --upgrade-strategy eager optimum[habana]

You can find examples in thedocumentation and in theexamples.

Before you begin, make sure you have all the necessary libraries installed :

pip install --upgrade --upgrade-strategy eager optimum[neuronx]

You can find examples in thedocumentation and in thetutorials.