support-new-model

Official

Add a new LLM or VLM to LMDeploy PyTorch.

AuthorInternLM
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This guide enables developers to extend LMDeploy by adding a new LLM or VLM to the PyTorch backend, streamlining the end-to-end integration from model code to deployment configuration.

Core Features & Use Cases

  • Provides a repeatable process to implement a new model file, register it in module_map, optionally supply a non-standard HF config builder, and add quantization mappings.
  • Supports both LLMs and VLMs, including necessary VLM preprocessors and architecture registration for end-to-end deployment.
  • Useful for teams expanding model families, performing experiments, or onboarding new architectures into production LMDeploy pipelines.

Quick Start

Follow the steps in the guide to add a new model to LMDeploy and verify it loads correctly.

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: support-new-model
Download link: https://github.com/InternLM/lmdeploy/archive/main.zip#support-new-model

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 471,000+ vetted skills library on demand.