serving-llms-vllm

serving-llms-vllm is a skill for Claude Code, Codex from synthetic-sciences/openscience. It costs 75 tokens per session (2,542 once invoked), scanned A, a copy of serving-llms-vllm, Apache-2.0.

A serving system for running language models behind an API. It manages GPU memory and combines requests so the model can process many users efficiently.

In plain words
What is it for?
Use it to run offline generation, expose an OpenAI-compatible API, serve quantized models, and split work across GPUs.
Why use it?
It removes much of the work involved in turning a model into a production endpoint with good throughput and latency.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to run offline generation, expose an OpenAI-compatible API, serve quantized models, and split work across GPUs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synthetic-sciences/openscience/vllm
About the project

synthetic-sciences/openscience is an AI workbench that carries out scientific research by reading papers, forming hypotheses, writing and running code, conducting experiments, analyzing results, and preparing reports. Researchers use it for work in machine learning, biology, physics, and chemistry with remote or local models. Catalogue add-ons extend its scientific workflows through skills and instructions.

synthetic-sciences/openscience · 3,501 stars · on GitHub · openscience.sh

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.

Any agent
npx skills add synthetic-sciences/openscience --skill vllm
Clone the repo
git clone --depth 1 https://github.com/synthetic-sciences/openscience

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for serving-llms-vllm

README.md
[![agentmods](https://agentmods.dev/badge/skills/synthetic-sciences/openscience/vllm.svg)](https://agentmods.dev/skills/synthetic-sciences/openscience/vllm)
Your own site
<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/vllm"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/vllm.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,542 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 125
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
How audits are shown
Origin 84% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.02542
Opus 5 $0.00037 $0.01271
Sonnet 5 $0.00015 $0.00508
Haiku 4.5 $0.00007 $0.00254

Measured 4d ago against content hash 0ad5a3055ad0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

serving-llms-vllm scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:9090/metrics | grep vllm
Origin

This is a copy

84% identical to serving-llms-vllm — 53 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

backend/cli/skills/ml-inference/vllm/SKILL.md · 371 lines

How it starts

The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vLLM - High-Performance LLM Serving

Quick start

vLLM achieves 24x higher throughput than standard transformers through PagedAttention (block-based KV cache) and continuous batching (mixing prefill/decode requests).

Installation:

pip install vllm

Basic offline inference:

from vllm import LLM, SamplingParams

llm = LLM(model="meta-llama/Llama-3-8B-Instruct")
sampling = SamplingParams(temperature=0.7, max_tokens=256)

outputs = llm.generate(["Explain quantum computing"], sampling)
print(outputs[0].outputs[0].text)

OpenAI-compatible server:

vllm serve meta-llama/Llama-3-8B-Instruct

# Query with OpenAI SDK
python -c "
from openai import OpenAI
client = OpenAI(base_url='http://localhost:8000/v1', api_key='EMPTY')
print(client.chat.completions.create(
    model='meta-llama/Llama-3-8B-Instruct',
    messages=[{'role': 'user', 'content': 'Hello!'}]
).choices[0].message.content)
"

Common workflows

Workflow 1: Production API deployment

Copy this checklist and track progress:

Deployment Progress:
- [ ] Step 1: Configure server settings
- [ ] Step 2: Test with limited traffic
- [ ] Step 3: Enable monitoring
- [ ] Step 4: Deploy to production
- [ ] Step 5: Verify performance metrics

Step 1: Configure server settings

Choose configuration based on your model size:

# For 7B-13B models on single GPU
vllm serve meta-llama/Llama-3-8B-Instruct \
  --gpu-memory-utilization 0.9 \
  --max-model-len 8192 \
  --port 8000

# For 30B-70B models with tensor parallelism
vllm serve meta-llama/Llama-2-70b-hf \
  --tensor-parallel-size 4 \
  --gpu-memory-utilization 0.9 \
  --quantization awq \
  --port 8000

# For production with caching and metrics
vllm serve meta-llama/Llama-3-8B-Instruct \
  --gpu-memory-utilization 0.9 \
  --enable-prefix-caching \
  --enable-metrics \
  --metrics-port 9090 \
  --port 8000 \
  --host 0.0.0.0

Step 2: Test with limited traffic

Run load test before production:

Read the full file on GitHub · 371 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 4d ago First seen · 371 lines · 75 tokens per session scan A 0ad5a3055ad0

Subscribe to this mod's changes

serving-llms-vllm is a skill published in the GitHub repository synthetic-sciences/openscience (3,501 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 2,542 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 84% identical to serving-llms-vllm, differing in 53 lines, and is treated as a copy.

Related

Other skills, from other repositories

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

davila7/claude-code-templates · 75 tokens

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

OpenLAIR/dr-claw · 75 tokens

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

liortesta/ClawdAgent · 75 tokens

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

OpenLAIR/dr-claw-plugin-cc · 75 tokens

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

ihatesea69/HieuNghi-AI-Skills · 75 tokens

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Orchestra-Research/AI-Research-SKILLs · 75 tokens