skills.rest
Msabih
MsabihCOMMUNITY
Explore all skills by this author →
GitHub

cortex-m

Build, test, and export Cortex-M CMSIS-NN models for on-device inference.

Updated Apr 30, 2026
Search Tags:#testing#backend#quantization#export#cortex-m#cmsis-nn
One-click install
npx skills add https://github.com/Msabih/executorch --skill cortex-m-msabih
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cortex-m
Source: https://github.com/Msabih/executorch/tree/main/.claude/skills/cortex-m
Command: npx skills add https://github.com/Msabih/executorch --skill cortex-m-msabih

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Build, test, or develop the Cortex-M (CMSIS-NN) backend for on-device inference and model deployment.

Core Features & Use Cases

  • End-to-end Cortex-M backend workflow including quantization with CortexMQuantizer, graph passes with CortexMPassManager, and model export to Cortex-M targets.
  • Use cases cover developing, testing, and exporting CMSIS-NN backed models for Cortex-M devices.

Quick Start

Quantize a sample model for Cortex-M, apply CMSIS-NN passes, and export the result for Cortex-M targets.

Frequently Asked Questions about cortex-m

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

FAQPage Schema
How do I quantize and export a model for Cortex-M CMSIS-NN on-device inference?▼

To quantize and export a model for Cortex-M CMSIS-NN on-device inference, use the CortexMQuantizer for quantization, apply graph passes via CortexMPassManager, and utilize export utilities to output the final model.

What is the Cortex-M CMSIS-NN backend pipeline used for?▼

The Cortex-M CMSIS-NN backend pipeline is used for developing, testing, and exporting models to enable on-device inference on Cortex-M targets. It provides a complete quantization and export workflow.

Can I run tests for the Cortex-M backend during development?▼

Yes, you can run Cortex-M tests during backend development. The workflow supports testing within the backends/cortex_m/ directory to validate models before exporting them to Cortex-M targets.

Do I need specific graph passes to export CMSIS-NN backed models to Cortex-M targets?▼

Yes, exporting CMSIS-NN backed models to Cortex-M targets requires applying specific graph passes. The CortexMPassManager handles these passes to prepare the quantized model for final export.

What is the best way to build and develop the Cortex-M backend?▼

The best way to build and develop the Cortex-M backend is by working within the backends/cortex_m/ directory, leveraging the CortexMQuantizer and CortexMPassManager to construct, test, and export the inference pipeline.

Why use CortexMQuantizer for on-device inference on Cortex-M devices?▼

CortexMQuantizer is used for on-device inference on Cortex-M devices to accurately quantize models. It integrates with the CortexMPassManager to ensure CMSIS-NN compatibility before final export.

Related Skills

Explore More Software Engineering Skills→
pytorchpytorch
4.9k

cortex-m

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

Official
Advanced
huahai2022huahai2022

cortex-m

Quantize and export PyTorch neural networks for Cortex-M targets using CMSIS-NN backends.

Community
Advanced
Vegetable-bird10086Vegetable-bird10086

cortex-m

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

Community
Advanced
melissa-pereira-deelmelissa-pereira-deel

On-Device ML Optimization

Optimize on-device ML models for speed, size, and energy efficiency.

Community
Advanced