Beginner Pathway#
Welcome to ExecuTorch. This pathway is designed for engineers who are comfortable with PyTorch but are new to on-device deployment. You will follow a structured, step-by-step sequence that builds foundational knowledge before introducing more complex topics.
Estimated time to complete: 2–4 hours for the core sequence. Individual steps can be done independently.
What You Will Learn#
By following this pathway, you will be able to:
Understand what ExecuTorch is and why it exists
Install ExecuTorch and set up your development environment
Export a PyTorch model to the
.pteformatRun inference using the Python runtime
Deploy a model to Android or iOS
Know where to go next based on your use case
Core Learning Sequence#
Work through these steps in order. Each step builds on the previous one.
Step 1 — Understand ExecuTorch (15 min)#
Before writing any code, read the conceptual overview to understand the ExecuTorch workflow and its key benefits.
High-level introduction to ExecuTorch’s purpose, design principles, and where it fits in the PyTorch ecosystem.
Difficulty: Beginner
A technical walkthrough of the three-stage pipeline: export, compilation, and runtime execution.
Difficulty: Beginner
Step 2 — Set Up Your Environment (20 min)#
Install ExecuTorch and verify your setup before attempting to export a model.
Install the ExecuTorch Python package, export a MobileNet V2 model using XNNPACK, and run your first inference. This is the canonical entry point for all new users.
Difficulty: Beginner | Prerequisites: Python 3.10–3.13, PyTorch, g++7+ or clang5+
Tip: If you encounter build errors or platform-specific issues during installation, consult the Frequently Asked Questions page before proceeding.
Step 3 — Understand Core Concepts (20 min)#
A brief review of the key concepts and terminology used throughout ExecuTorch documentation.
Definitions for Export IR, Edge Dialect, delegates, partitioners, .pte files, and other ExecuTorch-specific terms you will encounter throughout the documentation.
Difficulty: Beginner
Step 4 — Export Your First Model (30 min)#
Learn the standard export workflow using torch.export and to_edge_transform_and_lower.
The complete guide to exporting a PyTorch model for ExecuTorch, including backend selection, quantization basics, and handling dynamic shapes.
Difficulty: Intermediate | Builds on: Step 2
Use ModelExplorer to inspect your exported model graph and verify the export result before deployment.
Difficulty: Beginner
Step 5 — Deploy to Your Target Platform (30–60 min)#
Choose the platform you are targeting and follow the appropriate guide.
Integrate ExecuTorch into an Android app using the Java/Kotlin bindings. Includes Gradle dependency setup and the Module API.
Difficulty: Intermediate
Add ExecuTorch to an iOS or macOS project via Swift Package Manager. Covers Objective-C and Swift integration.
Difficulty: Intermediate
Run inference directly from Python using the ExecuTorch runtime bindings — the fastest way to validate a model before mobile deployment.
Difficulty: Beginner
Step 6 — Explore a Complete Example (optional, 30 min)#
Seeing a complete end-to-end example reinforces the concepts from the previous steps.
A self-contained tutorial that exports an MNIST model and runs it on a Raspberry Pi Pico2. Excellent for understanding the full pipeline on constrained hardware.
Difficulty: Beginner (hardware required)
An interactive Colab notebook covering the complete export, lowering, and verification workflow for MobileNet V2. No local setup required.
Difficulty: Beginner
Frequently Encountered Issues#
New users commonly encounter the following issues. Consult these resources before opening a support request.
Issue |
Resource |
|---|---|
Installation fails or package not found |
Frequently Asked Questions — Installation section |
Export fails with unsupported operator error |
Model Export and Lowering — Operator support section |
Model produces incorrect output after export |
Developer Tools Usage Tutorials — Numerical debugging |
Build errors on Windows |
Getting Started with ExecuTorch — Windows prerequisites note |
Backend not accelerating as expected |
Backends — Backend selection guide |
Where to Go Next#
Once you have completed the core sequence, choose your next direction based on your use case.
Export and deploy Llama, Phi, Qwen, and other LLMs to mobile and edge devices.
Use XNNPACK, Core ML, Qualcomm, Vulkan, and other backends for hardware-accelerated inference.
Quantization, memory planning, custom compiler passes, and backend development.
