skills.rest
Arm-Examples
Arm-ExamplesOFFICIAL
Explore all skills by this author →
GitHub

llm-backend-scaffold

Scaffolds new LLM backends into the LLM-Runner repository.

4|3|Updated Feb 18, 2026
Search Tags:#developer tools#scaffolding#llm#framework#cmake#backend integration
One-click install
npx skills add https://github.com/Arm-Examples/LLM-Runner --skill llm-backend-scaffold
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-backend-scaffold
Source: https://github.com/Arm-Examples/LLM-Runner/tree/main/skills/llm-backend-scaffold
Command: npx skills add https://github.com/Arm-Examples/LLM-Runner --skill llm-backend-scaffold

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a structured process and checklist for integrating new Large Language Model (LLM) backends or frameworks into the LLM-Runner repository, streamlining the development workflow.

Core Features & Use Cases

  • Backend Integration: Guides users through adding new LLM frameworks as in-tree wrappers or external dependencies.
  • Configuration Management: Details how to wire CMake routing, define configuration options, and manage model configuration files.
  • Testing and Documentation: Ensures new backends are properly tested and documented within the repository.
  • Use Case: A developer needs to add support for a new LLM inference engine (e.g., a custom-built one) to the LLM-Runner. This Skill provides the exact steps and checklist to ensure seamless integration, including CMake configuration, model file setup, and testing.

Quick Start

Follow the backend integration checklist to add a new LLM framework to the repository.

Frequently Asked Questions about llm-backend-scaffold

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

FAQPage Schema
How do I integrate a new LLM backend into a CMake-based repository?▼

Integrating a new LLM backend involves adding directories under src/cpp/frameworks, wiring LLM_FRAMEWORK routing, defining configuration options, and setting up tests for seamless framework support.

What does scaffolding an LLM framework wrapper involve?▼

Scaffolding an LLM framework wrapper involves managing in-tree wrappers or external dependencies, handling model downloads, managing configuration files, and updating repository documentation.

How do I configure CMake routing for a new ML inference engine?▼

Configuring CMake routing for a new ML inference engine requires wiring LLM_FRAMEWORK routing and defining specific configuration options to manage the new backend's build process.

Do I need to manage model configuration files when adding an LLM framework?▼

Yes, you need to manage model configuration files when adding an LLM framework to handle model downloads and ensure the new backend operates correctly within the repository.

What is the best way to ensure a new LLM backend is properly tested?▼

The best way to ensure a new LLM backend is properly tested is to follow a structured integration checklist that includes setting up specific tests and updating repository documentation.

Can I add a custom-built LLM inference engine as an external dependency?▼

You can add a custom-built LLM inference engine as an external dependency by scaffolding the integration, wiring CMake routing, and defining the necessary configuration options.

Related Skills

Explore More Software Engineering Skills→
NVIDIA-OmniverseNVIDIA-Omniverse
201

project-setup-c

Scaffold a CMake C/C++ project with ovrtx dependencies.

Official
Intermediate
soulmachinesoulmachine
3

llm-inference-benchmark

Benchmark OpenAI-compatible LLM inference servers and analyze saturation curves.

Community
Advanced
huggingfacehuggingface
10.9k

hugging-face-cli

Manage Hugging Face Hub resources via the hf CLI.

Official
Intermediate
k4drwk4drw
33

hc-new-widget

Automate HamClock-Next widget creation and integration via MCP scaffolding and REGISTER_WIDGET.

Community
Advanced