coreml-profile

Community

Analyze CoreML model performance on Apple Silicon

Authormattmireles
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps identify the compute units (ANE, GPU, CPU) used by CoreML models, detect silent fallback, and uncover performance bottlenecks on Apple Silicon devices.

Core Features & Use Cases

  • Compute Unit Analysis: Determines which compute units are active, including ANE, GPU, and CPU.
  • Performance Bottlenecks: Identifies issues such as silent fallback and inefficient model usage.
  • Use Case: When you want to optimize your CoreML model's performance and understand its behavior on Apple Silicon hardware.

Quick Start

Profile the 'kokoro_decoder_har_post_30s.mlpackage' model for silent fallback and performance issues.

Dependency Matrix

Required Modules

coremltoolsnumpypowermetricsxctrace

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: coreml-profile
Download link: https://github.com/mattmireles/kokoro-coreml/archive/main.zip#coreml-profile

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.