vllm-input-modalities

Official

Publish and test vLLM non-chat endpoints.

Authorair-gapped
Version1.0.0
Installs0

System Documentation

What problem does it solve?

vLLM non-chat surfaces — embeddings, reranking, STT, and OCR — are exposed and tested together to streamline deployment, validation, and operator-day workflows.

Core Features & Use Cases

  • Unified exposure of vLLM endpoints for embedding, reranking, ASR, and OCR workflows.
  • Quick validation and sample end-to-end scenarios for operators deploying multimodal models.
  • Clear references and example configurations to accelerate production rollout.

Quick Start

Run the probe-endpoint.sh script to validate pooling endpoints and confirm vLLM surfaces are live.

Dependency Matrix

Required Modules

curlpython

Components

scriptsreferences

💻 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-input-modalities
Download link: https://github.com/air-gapped/skills/archive/main.zip#vllm-input-modalities

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.