Skip to content

Python bindings

Info

API reference pages for IREE's runtime and compiler Python APIs are hosted on readthedocs.

Overview

IREE offers Python bindings split into several packages, covering different components:

PIP package name Description
iree-compiler IREE's generic compiler tools and helpers
iree-runtime IREE's runtime, including CPU and GPU backends
iree-tools-tf Tools for importing from TensorFlow
iree-tools-tflite Tools for importing from TensorFlow Lite
iree-tools-xla Tools for importing from XLA
iree-jax Tools for importing from JAX

Collectively, these packages allow for importing from frontends, compiling towards various targets, and executing compiled code on IREE's backends.

Warning

The TensorFlow, TensorFlow Lite, and XLA packages are currently only available on Linux and macOS. They are not available on Windows yet (see this issue).

Prerequisites

To use IREE's Python bindings, you will first need to install Python 3 and pip, as needed.

Tip

We recommend using virtual environments to manage python packages, such as through venv (about, tutorial):

python -m venv .venv
source .venv/bin/activate
python -m venv .venv
.venv\Scripts\activate.bat

When done, run deactivate.

Next, install packages:

python -m pip install --upgrade pip
python -m pip install numpy absl-py

Installing IREE packages

Prebuilt packages

Stable release packages are published to PyPI.

To install just the core IREE packages:

python -m pip install \
  iree-compiler \
  iree-runtime

To install IREE packages with tools for all frontends:

python -m pip install \
  iree-compiler \
  iree-runtime \
  iree-tools-tf \
  iree-tools-tflite \
  iree-tools-xla

Tip

Nightly packages are also published on GitHub releases. To use these, run pip install with this extra option:

--find-links https://github.com/google/iree/releases

Building from source

See Building Python bindings page for instructions for building from source.

Using the Python bindings

API reference pages for IREE's runtime and compiler Python APIs are hosted on readthedocs.

Check out the samples in IREE's colab/ directory and the iree-samples repository for examples using the Python APIs.

Back to top