Installation

We recommend installing Olive in a virtual environment or a conda environment. Olive is installed using pip.

Create a virtual/conda environment with the desired version of Python and activate it.

You will need to install a build of onnxruntime. You can install the desired build separately but public versions of onnxruntime can also be installed as extra dependencies during Olive installation.

Install with pip

Olive is available for installation from PyPI.

pip install olive-ai[auto-opt,finetune,capture-onnx-graph,bnb]
pip install transformers datasets onnxscript

Optional Dependencies

Olive has optional dependencies that can be installed to enable additional features. Please refer to Olive package config for the list of extras and their dependencies.

Install from source

Install the latest main version of Olive from source. Please note that this is a development version and may not be stable.

pip install git+https://github.com/microsoft/Olive

With onnxruntime (Default CPU):

pip install git+https://github.com/microsoft/Olive#egg=olive-ai[cpu]

With onnxruntime-gpu:

pip install git+https://github.com/microsoft/Olive#egg=olive-ai[gpu]

With onnxruntime-directml:

pip install git+https://github.com/microsoft/Olive#egg=olive-ai[directml]

Editable install

If you want contribute to Olive and test your code, you can install Olive in editable mode.

Clone the repository and install Olive with the following commands:

git clone https://github.com/microsoft/Olive
cd Olive
pip install -e .