MLIA Ethos-U

Purpose

mlia-ethos-u extends MLIA with Ethos-U target knowledge and the backend plugins needed for Vela and Corstone-based analysis flows, including supported ExecuTorch AOT runs through Corstone.

Start here: Arm Learning Path

Analyze machine learning models for Arm Ethos-U with Arm ML Inference Advisor

Follow this hands-on guide to discover target profiles and backends, check model compatibility, and interpret Vela estimates and Corstone performance results.

Documentation Map

• Target profiles
• Backends
• Outputs and metrics
• CLI examples
• Troubleshooting
• Development

The Ethos-U Python API walkthrough notebook is available as a download for interactive use. It is not part of the MkDocs navigation because the documentation build does not render notebooks.

For shared CLI, installation, and plugin architecture guidance, see the MLIA core documentation.