skillfed

pte-adapter-model-explorer

Adapter for Model Explorer to support PTE files for Ethos-U and VGF targets

pte-adapter-model-explorer v0.1.2 92.8K downloads/30d#13,429 on PyPI1
Permissive license Apache-2.0 Active released

What it is and what it does

This package is a plugin for Model Explorer that adds support for visualizing PyTorch Executorch PTE files. It integrates with Model Explorer's extension system to enable inspection and debugging of neural network models compiled for specific hardware targets: Arm Ethos-U NPU, Arm VGF, and XNNPACK backends.

You install it alongside ai-edge-model-explorer and activate it via a command-line flag. Once enabled, it allows you to load and inspect PTE files in Model Explorer's graphical interface, making it useful for developers working with Executorch models on Arm hardware or XNNPACK targets. The package depends on ai-edge-model-explorer, vgf-adapter-model-explorer, tosa-adapter-model-explorer, and flatbuffers, and runs on Linux, macOS, and Windows.

Use it for:

  • Visualize and debug Executorch models compiled for Arm Ethos-U NPU deployment.
  • Inspect model graphs and operations for Arm VGF backend targets.
  • Analyze XNNPACK-compiled models in a graphical interface.
  • Verify model structure and layer connectivity before deploying to edge devices.
  • Troubleshoot model compilation issues by examining the resulting PTE file structure.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Extends Model Explorer with visualization support for PyTorch Executorch PTE files targeting Arm Ethos-U NPU, Arm VGF, and XNNPACK backends.

Yes, if you work with PyTorch Executorch models targeting Arm or XNNPACK backends and need to visualize or debug them. The package is actively maintained, has low install friction, carries a permissive license, and integrates cleanly into Model Explorer. The Beta status and small user base suggest it is specialized rather than production-hardened, so verify it supports your specific backend before committing.

Install

pte-adapter-model-explorer on PyPI

pip

pip install pte-adapter-model-explorer

uv

uv add pte-adapter-model-explorer

poetry

poetry add pte-adapter-model-explorer

Installing pte-adapter-model-explorer

Before you install

Low friction install with a pure-Python wheel. Active maintenance with recent releases. Requires Python >=3.10, <3.13 and runs on Linux, macOS, and Windows.

License in practice

Apache-2.0 permissive license allows commercial and private use with minimal restrictions.

Quickstart

pip install pte-adapter-model-explorer ai-edge-model-explorer
model-explorer --extensions=pte_adapter_model_explorer

Requires Python >=3.10, <3.13. ai-edge-model-explorer must be installed separately.

Verify before relying

  • Whether the adapter works with all three backends equally well or has known limitations.
  • Performance characteristics when visualizing large PTE models.
  • Whether the adapter is production-ready despite Beta development status.

Package facts

License Apache-2.0 (permissive)
Python support capped below the current Python release (<3.13,>=3.10)
Install friction low — pure-Python wheel
Runtime dependencies 4 — ai-edge-model-explorer, vgf-adapter-model-explorer, tosa-adapter-model-explorer, flatbuffers
Maintenance actively maintained — 36 days since the last release
Last repo commit
First released
Downloads 92,757/month — #13,429 on PyPI (30-day window, as of 2026-08-14)
Known vulnerabilities none known (OSV.dev, checked 2026-08-14)

Evidence: pte_adapter_model_explorer-0.1.2-py3-none-any.whl

Keywords: model-explorer, ethos, pte, visualization

Development Status :: 4 - BetaIntended Audience :: DevelopersOperating System :: POSIX :: LinuxProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12

Tags

pte file visualizationmodel explorer adapterexecutorch model debuggingarm ethos-u visualizationneural network model inspectionpytorch executorch tools
model-visualizationexecutorchedge-ai

More Artificial Intelligence packages