1

4

Note

Before diving in, make sure you understand the concepts in the ExecuTorch Overview

Setting Up ExecuTorch¶

In this section, we’ll learn how to

Set up an environment to work on ExecuTorch
Generate a sample ExecuTorch program
Build and run a program with the ExecuTorch runtime

System Requirements¶

Operating System¶

We’ve tested these instructions on the following systems, although they should also work in similar environments.

Linux (x86_64)

CentOS 8+
Ubuntu 20.04.6 LTS+
RHEL 8+

macOS (x86_64/M1/M2)

Big Sur (11.0)+

Windows (x86_64)

Windows Subsystem for Linux (WSL) with any of the Linux options

Software¶

conda or another virtual environment manager
- We recommend conda as it provides cross-language support and integrates smoothly with pip (Python’s built-in package manager)
- Otherwise, Python’s built-in virtual environment manager python venv is a good alternative.
g++ version 8 or higher, clang++ version 8 or higher, or another C++17-compatible toolchain that supports GNU C-style statement expressions (({ ... }) syntax).

Note that the cross-compilable core runtime code supports a wider range of toolchains, down to C++11. See the Runtime Overview for portability details.

Environment Setup¶

Create a Virtual Environment¶

Install conda on your machine. Then, create a virtual environment to manage our dependencies.

# Create and activate a conda environment named "executorch"
conda create -yn executorch python=3.10.0
conda activate executorch

Clone and install ExecuTorch requirements¶

# Clone the ExecuTorch repo from GitHub
git clone --branch v0.2.0 https://github.com/pytorch/executorch.git
cd executorch

# Update and pull submodules
git submodule sync
git submodule update --init

# Install ExecuTorch pip package and its dependencies, as well as
# development tools like CMake.
./install_requirements.sh

Use the --pybind flag to install with pybindings and dependencies for other backends.

./install_requirements.sh --pybind <coreml | mps | xnnpack>

After setting up your environment, you are ready to convert your PyTorch programs to ExecuTorch.

Create an ExecuTorch program¶

After setting up your environment, you are ready to convert your PyTorch programs to ExecuTorch.

Export a Program¶

ExecuTorch provides APIs to compile a PyTorch nn.Module to a .pte binary consumed by the ExecuTorch runtime.

torch.export
exir.to_edge
exir.to_executorch
Save the result as a .pte binary to be consumed by the ExecuTorch runtime.

Let’s try this using with a simple PyTorch model that adds its inputs. Create a file called export_add.py with the following code:

import torch
from torch.export import export
from executorch.exir import to_edge

# Start with a PyTorch model that adds two input tensors (matrices)
class Add(torch.nn.Module):
  def __init__(self):
    super(Add, self).__init__()

  def forward(self, x: torch.Tensor, y: torch.Tensor):
      return x + y

# 1. torch.export: Defines the program with the ATen operator set.
aten_dialect = export(Add(), (torch.ones(1), torch.ones(1)))

# 2. to_edge: Make optimizations for Edge devices
edge_program = to_edge(aten_dialect)

# 3. to_executorch: Convert the graph to an ExecuTorch program
executorch_program = edge_program.to_executorch()

# 4. Save the compiled .pte program
with open("add.pte", "wb") as file:
    file.write(executorch_program.buffer)

Then, execute it from your terminal.

python3 export_add.py

See the ExecuTorch export tutorial to learn more about the export process.

Build & Run¶

After creating a program, we can use the ExecuTorch runtime to execute it.

For now, let’s use executor_runner, an example that runs the forward method on your program using the ExecuTorch runtime.

Build Tooling Setup¶

The ExecuTorch repo uses CMake to build its C++ code. Here, we’ll configure it to build the executor_runner tool to run it on our desktop OS.

# Clean and configure the CMake build system. Compiled programs will appear in the executorch/cmake-out directory we create here.
(rm -rf cmake-out && mkdir cmake-out && cd cmake-out && cmake ..)

# Build the executor_runner target
cmake --build cmake-out --target executor_runner -j9

Run Your Program¶

Now that we’ve exported a program and built the runtime, let’s execute it!

./cmake-out/executor_runner --model_path add.pte

Our output is a torch.Tensor with a size of 1. The executor_runner sets all input values to a torch.ones tensor, so when x=[1] and y=[1], we get [1]+[1]=[2]

To learn how to build a similar program, visit the ExecuTorch in C++ Tutorial.

[Optional] Setting Up Buck2¶

Buck2 is an open-source build system that some of our examples currently utilize for building and running.

However, please note that the installation of Buck2 is optional for using ExecuTorch and we are in the process of transitioning away from Buck2 and migrating all relevant sections to cmake. This section will be removed once we finish the migration.

To set up Buck2, You will need the following prerequisits for this section:

The zstd command line tool — install by running
```
pip3 install zstd
```
Version 2024-02-15 of the buck2 commandline tool — you can download a prebuilt archive for your system from the Buck2 repo. Note that the version is important, and newer or older versions may not work with the version of the buck2 prelude used by the ExecuTorch repo.

Configure Buck2 by decompressing with the following command (filename depends on your system):

# For example, buck2-x86_64-unknown-linux-musl.zst or buck2-aarch64-apple-darwin.zst
zstd -cdq buck2-DOWNLOADED_FILENAME.zst > /tmp/buck2 && chmod +x /tmp/buck2

You may want to copy the buck2 binary into your $PATH so you can run it as buck2.

After the installation, you can run the add.pte program by following buck2 command:

/tmp/buck2 run //examples/portable/executor_runner:executor_runner -- --model_path add.pte

Next Steps¶

Congratulations! You have successfully exported, built, and run your first ExecuTorch program. Now that you have a basic understanding of ExecuTorch, explore its advanced features and capabilities below.

Build an Android or iOS demo app
Learn more about the export process
Dive deeper into the Export Intermediate Representation (EXIR) for complex export workflows
Refer to advanced examples in executorch/examples