skills.rest
Vegetable-bird10086
Vegetable-bird10086COMMUNITY
Explore all skills by this author →
GitHub

cortex-m

Develop and deploy quantized AI models for Cortex-M microcontrollers with CMSIS-NN.

Updated Apr 23, 2026
Search Tags:#embedded#quantization#microcontroller#cortex-m#cmsis-nn#model export
One-click install
npx skills add https://github.com/Vegetable-bird10086/executorch-pd --skill cortex-m-vegetable-bird10086
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cortex-m
Source: https://github.com/Vegetable-bird10086/executorch-pd/tree/main/.claude/skills/cortex-m
Command: npx skills add https://github.com/Vegetable-bird10086/executorch-pd --skill cortex-m-vegetable-bird10086

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires torch, executorch, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Facilitates the building, testing, and exporting of models for Cortex-M microcontrollers using CMSIS-NN, streamlining embedded AI deployment.

Core Features & Use Cases

  • Backend Development: Allows developing custom Cortex-M backends with support for quantization and graph rewriting.
  • Model Export & Testing: Supports exporting models, applying passes, and verifying correctness through tests on simulation hardware.
  • Use Case: Deploy machine learning models directly onto resource-constrained Cortex-M devices for real-time inference in IoT applications.

Quick Start

Use the cortex-m skill to export a quantized model for Cortex-M and run tests on the target hardware.

Frequently Asked Questions about cortex-m

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I export a quantized AI model for Cortex-M microcontrollers?▼

To export a quantized model for Cortex-M microcontrollers, you can apply model quantization and graph rewriting passes to transform your AI model, then verify its correctness through tests on simulation hardware.

What is CMSIS-NN integration for embedded AI deployment?▼

CMSIS-NN integration is the process of adapting machine learning models through backend development and graph rewriting to enable efficient real-time inference directly on resource-constrained Cortex-M devices.

Does this workflow support developing custom Cortex-M backends with PyTorch?▼

Yes, the workflow supports developing custom Cortex-M backends using PyTorch and ExecuTorch, allowing you to implement quantization and graph rewriting tailored for CMSIS-NN integration.

Can I run machine learning inference directly on IoT microcontrollers?▼

You can deploy machine learning models directly onto resource-constrained Cortex-M devices for real-time inference in IoT applications by utilizing the provided scripts and reference implementations.

What's the best way to verify model correctness before deploying to embedded hardware?▼

The best way to verify model correctness is by exporting the model, applying the necessary transformation passes, and running validation tests on simulation hardware to ensure accurate inference behavior.

Related Skills

Explore More Software Engineering Skills→
hung-phanhung-phan
1

keras

Prototype and train neural networks using high-level Keras APIs.

Community
Advanced
MayaDispelerMayaDispeler
3

embedded-systems-patterns

Provide embedded systems development guidelines for resource-constrained environments and real-time patterns.

Community
Advanced
Vegetable-bird10086Vegetable-bird10086

binary-size

Analyze and reduce ExecuTorch binary size using bloaty and nm.

Community
Intermediate
pytorchpytorch
4.9k

cortex-m

Quantize and export PyTorch models for Cortex-M CMSIS-NN targets using PT2E flow and CortexMPassManager.

Official
Advanced