vllm-omni
OfficialDisaggregate multimodal serving with vLLM-Omni.
Authorair-gapped
Version1.0.0
Installs0
System Documentation
What problem does it solve?
vLLM-Omni enables operators to deploy and operate disaggregated, multimodal inference pipelines that support image, video, and audio modalities at scale.
Core Features & Use Cases
- End-to-end multimodal serving: /v1/images/generations, /v1/videos, /v1/audio/speech, /v1/realtime.
- Stage-based disaggregation: Thinker → Talker → Code2Wav (or AR → DiT) with OmniConnector.
- Model support and config: supports Qwen3-Omni, FLUX, Wan2.2, BAGEL, GLM-Image, etc; quantization, LoRA, frame interpolation, diffusion schedulers.
- Reference materials: endpoints, models, stage-configs, diffusion docs.
Quick Start
Start a local vLLM-Omni deployment using a prepared stage-config YAML and point clients at the Omni-enabled endpoint.
Dependency Matrix
Required Modules
None requiredComponents
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 Download link: https://github.com/air-gapped/skills/archive/main.zip#vllm-omni Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.