vllm-omni-multimodal

Community

Multi-modal AI for text, image, audio, and video.

Authorhsliuustc0106
Version1.0.0
Installs0

System Documentation

What problem does it solve?

End-to-end multimodal AI workloads often require separate tools for text, image, audio, and video processing. This skill unifies those capabilities under one Omni-model workflow to simplify development and inference.

Core Features & Use Cases

  • End-to-end multimodal reasoning and generation across text, image, audio, and video inputs using Qwen Omni models.
  • Quick-start examples for offline and online deployment and multi-turn conversations.
  • Supports multiple model variants with different VRAM requirements and serving modes.

Quick Start

Initialize an Omni session with a Qwen-Omni model and ask a text question to begin a multi-modal conversation.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: vllm-omni-multimodal
Download link: https://github.com/hsliuustc0106/vllm-omni-skills/archive/main.zip#vllm-omni-multimodal

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.