fastdeploy-llm-integration

Official

Add LLM deployment support to FastDeploy.

AuthorPaddlePaddle
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Guides you through adding inference deployment support for a new open-source LLM to the FastDeploy repository. Given a model path (local or HuggingFace/ModelScope hub), this skill walks through analyzing the model architecture, choosing the right base class, generating the model implementation file, updating registries, writing docs, and producing a deployment test script.

Core Features & Use Cases

  • Analyze a model's architecture and select the appropriate base class.
  • Generate model implementation files, update registries, write documentation, and create a deployment test script.
  • Use case: port a HuggingFace/ModelScope LLM to FastDeploy and validate the integration with a deployment test.

Quick Start

Provide the model path (local or hub) and follow the guided steps to generate the FastDeploy integration artifacts.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: fastdeploy-llm-integration
Download link: https://github.com/PaddlePaddle/FastDeploy/archive/main.zip#fastdeploy-llm-integration

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 510,000+ vetted skills library on demand.