binary-size

Analyze and reduce ExecuTorch binary size using bloaty and nm.

Updated Apr 23, 2026

Search Tags:#performance #optimization #build #embedded #cmake #binary #size

Ready to run

npx skills add https://github.com/Vegetable-bird10086/executorch-pd --skill binary-size-vegetable-bird10086

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: binary-size
Source: https://github.com/Vegetable-bird10086/executorch-pd/tree/main/.claude/skills/binary-size
Command: npx skills add https://github.com/Vegetable-bird10086/executorch-pd --skill binary-size-vegetable-bird10086

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill assists in analyzing and reducing the size of ExecuTorch binaries, facilitating deployment on size-constrained devices and improving startup times.

Core Features & Use Cases

Binary Analysis: Uses tools like bloaty and nm to analyze the size contributions of different binary sections.
Size Reduction: Offers strategies for reducing static and dynamic binary sizes by optimizing build flags and code structure.
Use Case: When preparing ExecuTorch for deployment on microcontrollers, employ this Skill to ensure the binary meets required size limits without sacrificing core functionality.

Quick Start

Ask the user to specify the path to the executorch repo to begin the size analysis.

Frequently Asked Questions about binary-size

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

FAQPage Schema

How do I reduce ExecuTorch binary size for microcontroller deployment?▼

You can reduce ExecuTorch binary size for microcontroller deployment by applying size optimization strategies via standard CMake build configurations. Specify the repository path to begin static and dynamic footprint analysis and optimization.

What is the best way to analyze binary size contributions in an embedded AI runtime?▼

The best way to analyze binary size contributions in an embedded AI runtime is using tools like bloaty and nm. They break down size contributions across different binary sections to identify optimization targets.

Do I need bloaty and nm to optimize ExecuTorch build flags?▼

Yes, you need bloaty and nm to analyze size contributions and optimize ExecuTorch build flags effectively. They provide the necessary section breakdown to guide CMake size optimization configurations for constrained deployments.

Can I use CMake size optimizations without sacrificing core AI runtime functionality?▼

Yes, you can use CMake size optimizations without sacrificing core AI runtime functionality by applying targeted code structure and build flag adjustments. This ensures binaries meet required limits for deployment while retaining essential features.

Why does my ExecuTorch binary exceed size limits for embedded systems?▼

Your ExecuTorch binary may exceed size limits for embedded systems due to unoptimized build flags and unanalyzed code structures. Running bloaty and nm helps identify large binary sections for targeted size reduction strategies.