Analyze machine learning models for Arm Ethos-U with Arm ML Inference Advisor
Introduction
Understand where MLIA fits in model preparation
Install MLIA and discover capabilities
Analyze LiteRT artifacts with MLIA and Vela
Analyze TOSA IR artifacts with MLIA and Vela
Analyze ExecuTorch artifacts with MLIA and Corstone
(Optional) Use the MLIA Python API
Next Steps
Analyze machine learning models for Arm Ethos-U with Arm ML Inference Advisor
Who is this for?
This Learning Path is for ML developers who want to use the Arm ML Inference Advisor (MLIA) to evaluate whether a model is suitable for a target before moving into deployment, graph inspection, or runtime profiling.
What will you learn?
Upon completion of this Learning Path, you will be able to:
- Use the MLIA CLI to discover target profiles and backends.
- Run compatibility and performance analysis on LiteRT, Tensor Operator Set Architecture (TOSA), and ExecuTorch artifacts.
- Interpret MLIA JSON output, advice, Vela estimates, and Corstone whole-model NPU performance counters.
- (Optional) Call the MLIA Python API from automation or other tools.
Prerequisites
Before starting, you will need the following:
- Ubuntu 22.04 LTS or another compatible Linux environment
- Python 3.10 or later
- Git and Git Large File Storage (LFS) to download the model artifacts
- Basic familiarity with machine learning model deployment concepts
- Basic familiarity with command-line tools
Summary
This summary was drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.
.pte artifacts with Corstone. You’ll learn that Vela provides compiler estimates and operator breakdowns, while Corstone reports whole-model NPU counters. Optionally, you’ll automate compatibility checks with the Python API.Frequently asked questions
These FAQs were drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.
git lfs version. If the command fails on Ubuntu, run sudo apt update, then install Git LFS and the Python development package with sudo apt install -y git-lfs python3.10-dev. Run git lfs install before you clone the repository and pull the model artifacts.source mlia_env/bin/activate, then run mlia --help to confirm that the CLI works. To list target profiles, run mlia target list. To see available and installed backends, run mlia backend list.accelerator_operator_percentage as 0. For the supplied INT8 model, Vela reports status as ok and accelerator_operator_percentage as 100.0 for the ethos-u85-256 profile.run_advisor() from the Python API when you want to integrate MLIA compatibility checks into a product, dashboard, workflow runner, or CI system.