ad-model-onboard

Official

Onboard HuggingFace models for AutoDeploy.

AuthorNVIDIA
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the complex process of converting HuggingFace models into a prefill-only AutoDeploy custom model format, ensuring compatibility and efficient deployment.

Core Features & Use Cases

  • Model Translation: Converts HuggingFace models to a prefill-only AutoDeploy format.
  • Custom Op Integration: Utilizes reference custom operations for compatibility.
  • Validation: Performs hierarchical equivalence tests to ensure accuracy.
  • Use Case: A machine learning engineer needs to deploy a new LLM from HuggingFace to a custom inference engine. This Skill handles the intricate conversion and validation steps, saving significant development time.

Quick Start

Use the ad-model-onboard skill to convert the HuggingFace model 'mistralai/Mistral-7B-v0.1' into a prefill-only AutoDeploy custom model.

Dependency Matrix

Required Modules

None required

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: ad-model-onboard
Download link: https://github.com/NVIDIA/TensorRT-LLM/archive/main.zip#ad-model-onboard

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 223,000+ vetted skills library on demand.