vllm-serving-setup

vllm-serving-setup is a skill for Claude Code from aws-samples/sample-oh-my-aidlcops. It costs 76 tokens per session (1,507 once invoked), scanned A, original, MIT-0.

A setup guide for running vLLM 0.18.2, software that serves AI models, on Amazon EKS, AWS's managed Kubernetes service. It covers settings for sharing GPU memory and processing many requests.

In plain words
What is it for?
Producing Helm configuration, monitoring setup, autoscaling settings, and kubectl checks for a vLLM service using features such as Multi-LoRA, FP8 KV Cache, chunked prefill, and continuous batching.
Why use it?
It provides the deployment settings and checks needed to configure an AI model server for production workloads on EKS.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the ai-infra plugin — 6 skills, 2 commands, 4 agents shipped together

About the project

sample-oh-my-aidlcops is a plugin marketplace for Claude Code and Kiro that packages practices for managing the AWS AI-Driven Development Lifecycle, including design correctness and agent safety. It is for teams using agents to develop and operate AWS systems with approval checkpoints. Its catalogue contains the marketplace's plugins, skills, agents, and commands.

aws-samples/sample-oh-my-aidlcops · 19 stars · on GitHub · aws-samples.github.io

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.

agentmods
npx agentmods add skills/aws-samples/sample-oh-my-aidlcops/vllm-serving-setup
Any agent
npx skills add aws-samples/sample-oh-my-aidlcops --skill vllm-serving-setup
Clone the repo
git clone --depth 1 https://github.com/aws-samples/sample-oh-my-aidlcops

Made for: Claude Code.

Or install ai-infra, the plugin that ships this one along with the rest of its 6 skills, 2 commands, 4 agents.

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 vllm-serving-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/aws-samples/sample-oh-my-aidlcops/vllm-serving-setup.svg)](https://agentmods.dev/skills/aws-samples/sample-oh-my-aidlcops/vllm-serving-setup)
Your own site
<a href="https://agentmods.dev/skills/aws-samples/sample-oh-my-aidlcops/vllm-serving-setup"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-oh-my-aidlcops/vllm-serving-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,507 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin unknown No closer match found 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 $0.00076 $0.01507
Opus 5 $0.00038 $0.00754
Sonnet 5 $0.00015 $0.00301
Haiku 4.5 $0.00008 $0.00151

Measured 6d ago against content hash 2ea3dc66f72f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

vllm-serving-setup 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 6d 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 -s http://localhost:8000/v1/models | jq
plugins/ai-infra/skills/vllm-serving-setup/SKILL.md · 124 lines

The source is not reproduced here

Licensed MIT-0

The repository is licensed MIT-0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 6d ago First seen · 124 lines · 76 tokens per session scan A 2ea3dc66f72f

Subscribe to this mod's changes

vllm-serving-setup is a skill published in the GitHub repository aws-samples/sample-oh-my-aidlcops (19 stars, last pushed 2d ago), licensed MIT-0. It adds 76 tokens to every session and 1,507 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

gpu-kubernetes-operations

Operate GPU-backed Kubernetes clusters for AI inference and training with scheduling, autoscaling, node health, MIG partitioning, and cost controls.

BagelHole/DevOps-Security-Agent-Skills · 33 tokens

model-serving-kubernetes

Deploy ML models on Kubernetes with KServe (formerly KFServing) and NVIDIA Triton Inference Server. Includes canary deployments, autoscaling, model versioning, A/B testing, and GPU resource management for production model serving.

BagelHole/DevOps-Security-Agent-Skills · 51 tokens

llm-inference-scaling

Auto-scale LLM inference clusters on Kubernetes using KEDA, custom GPU metrics, and horizontal pod autoscaling. Handle traffic spikes, implement queue-based scaling, and optimize cost with spot instances for AI workloads.

BagelHole/DevOps-Security-Agent-Skills · 48 tokens

aws-bedrock-ai

WORKFLOW SKILL — Amazon Bedrock and AWS AI design: foundation model selection, knowledge bases (RAG), agents for bedrock, guardrails, provisioned throughput, batch inference, fine-tuning, KMS, VPC endpoints, regional GA, and per-provider licensing.

odere-pro/claude-aws-architect · 65 tokens

ollama-stack

Run local LLM workloads with Ollama, Open WebUI, and GPU-aware tuning for private development environments. Use when setting up private inference, local AI dev environments, or air-gapped LLM deployments.

BagelHole/DevOps-Security-Agent-Skills · 46 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens