skills.rest
hsliuustc0106
hsliuustc0106COMMUNITY
Explore all skills by this author →
WebsiteGitHub

vllm-omni-api

Bridge client applications with the vLLM-Omni API using OpenAI-compatible endpoints.

84|27|Updated Mar 3, 2026
Search Tags:#api#multimodal#endpoints#openai-compatible#client-integration#vllm-omni
One-click install
npx skills add https://github.com/hsliuustc0106/vllm-omni-skills --skill vllm-omni-api
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vllm-omni-api
Source: https://github.com/hsliuustc0106/vllm-omni-skills/tree/main/skills/vllm-omni-api
Command: npx skills add https://github.com/hsliuustc0106/vllm-omni-skills --skill vllm-omni-api

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Bridge client applications with the vLLM-Omni API using OpenAI-compatible endpoints for multi-modal generation, simplifying integration and deployment.

Core Features & Use Cases

  • Chat completions for text, image, and audio through /v1/chat/completions.
  • Image generation via /v1/images/generations and optional image editing flows.
  • Text-to-speech via /v1/audio/speech and model discovery via /v1/models.
  • Example: Build a dashboard app that asks for a sunset image and reads back a generated description.

Quick Start

Create a small client that calls the /v1/chat/completions endpoint to start a chat session.

Frequently Asked Questions about vllm-omni-api

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I integrate vLLM-Omni into my existing application stack?▼

You can integrate vLLM-Omni by calling its OpenAI-compatible endpoints, such as /v1/chat/completions, to bridge your client applications with the multimodal API server for text, image, video, and audio generation.

Can I generate images and audio using OpenAI-compatible endpoints with vLLM-Omni?▼

Yes, vLLM-Omni supports multimodal generation through OpenAI-compatible endpoints, allowing you to generate images via /v1/images/generations and produce text-to-speech audio via /v1/audio/speech.

What is the best way to discover available models on a vLLM-Omni API server?▼

Model discovery is handled by calling the /v1/models endpoint, which queries the vLLM-Omni API server to return a list of available models for your client application to use.

Does vLLM-Omni API integration support health checks and error handling?▼

Yes, the vLLM-Omni API integration specifies how to handle health checks and error cases, ensuring your client applications can reliably manage failures when sending requests to the API server.

How do I build a client that handles chat completions for text and image inputs?▼

You can build a client that sends multimodal requests to the /v1/chat/completions endpoint, enabling your application to process text and image inputs and receive generated responses from the vLLM-Omni API.

Related Skills

Explore More Software Engineering Skills→
xiaomochnxiaomochn
198

model-config

Configure AI model providers and default model selection in openclaw.json.

Community
Intermediate
quanpersie2001quanpersie2001

ai-multimodal

Process multimodal media to extract text, transcriptions, and structured data.

Community
Advanced
luansilvadbluansilvadb

domain-exception-hierarchy

Define a three-tier domain exception hierarchy with adapter translation and retry handlers.

Community
Advanced
vllm-projectvllm-project
6.0k

vllm-omni-npu-model-runner-upgrade

Upgrade vllm-omni NPU model runners to align with vllm-ascend interfaces.

Official
Advanced