A software package for running large language models, which are programs that generate or understand text, images, and other inputs. vLLM can run models locally in batches or provide a server that accepts OpenAI-compatible requests.

Running offline batch inference, serving models through an OpenAI-compatible API, using LoRA adapters, processing multimodal inputs, generating embeddings, classification, structured output, and tool calling.

It provides one tool for several model-serving and inference tasks instead of requiring separate systems for each model interface.

vllm — Plugin by datathings

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add datathings/marketplace

agentmods

npx agentmods add plugins/datathings/marketplace/vllm

Clone the repo

git clone --depth 1 https://github.com/datathings/marketplace

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

vllm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/vllm/.claude-plugin/plugin.json · 14 lines

What it actually says

{
  "name": "vllm",
  "version": "3.0.4",
  "description": "vLLM v0.19.0 skill: offline batch inference, OpenAI-compatible server, LoRA adapters, multimodal inputs, embeddings, classification, structured outputs, and tool calling.",
  "author": {
    "name": "Datathings",
    "email": "[email protected]"
  },
  "license": "Apache-2.0",
  "repository": "https://github.com/datathings/marketplace",
  "keywords": ["python", "vllm", "llm-inference", "openai-compatible", "gpu"],
  "skills": "./skills/"
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 14 lines scan A 022a536b870e

Subscribe to this mod's changes

vllm is a plugin published in the GitHub repository datathings/marketplace (11 stars, last pushed 5d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIs

vllm

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

humanizer

nextjs

nextjs

claude-plugins-official

knowledge-work-plugins

ecc