serving-llms-vllm

serving-llms-vllm is a skill for Claude Code, Codex from davidtoby/agent-skills. It costs 27 tokens per session (2,506 once invoked), scanned A, a copy of serving-llms-vllm, MIT.

A tool for running language models as services that applications can call. It provides an OpenAI-compatible API and supports methods for using GPU memory efficiently.

In plain words
What is it for?
Use it to deploy LLM APIs, run offline model inference, serve quantized models, or distribute work across multiple GPUs.
Why use it?
It helps turn a downloaded language model into an API that can handle multiple requests and production workloads. It is intended to improve response capacity and manage limited GPU resources.

Skill for Claude CodeCodex

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

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/davidtoby/agent-skills/vllm.svg)](https://agentmods.dev/skills/davidtoby/agent-skills/vllm)
Your own site
<a href="https://agentmods.dev/skills/davidtoby/agent-skills/vllm"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/vllm.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,506 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin 89% 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 $0.00027 $0.02506
Opus 5 $0.00014 $0.01253
Sonnet 5 $0.00005 $0.00501
Haiku 4.5 $0.00003 $0.00251

Measured yesterday against content hash dbc02611b59f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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

89% identical to serving-llms-vllm — 34 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.

skills/mlops/inference/vllm/SKILL.md · 372 lines

How it starts

The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vLLM - High-Performance LLM Serving

When to use

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.

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

Read the full file on GitHub · 372 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. yesterday First seen · 372 lines · 27 tokens per session scan A dbc02611b59f

Subscribe to this mod's changes

serving-llms-vllm is a skill published in the GitHub repository davidtoby/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 2,506 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 89% identical to serving-llms-vllm, differing in 34 lines, and is treated as a copy.

Related

Other skills, from other repositories

ehr-analysis

End-to-end EHR predictive modeling pipeline with PyHealth, covering dataset loading, task definition, model training, evaluation, calibration, and clinical interpretation.

zongtingwei/Bioclaw_Skills_Hub · 33 tokens

bindcraft

End-to-end binder design using BindCraft hallucination. Use this skill when: (1) Designing protein binders with built-in AF2 validation, (2) Running production-quality binder campaigns, (3) Using different design protocols (fast, default, slow), (4) Need joint backbone and sequence optimization, (5) Want high…

zongtingwei/Bioclaw_Skills_Hub · 107 tokens

esm2-sequence-scoring

ESM2 protein language model for sequence scoring, embeddings, and plausibility checks. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) scores, (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing…

zongtingwei/Bioclaw_Skills_Hub · 111 tokens

scrna-preprocessing-clustering

Standard scRNA-seq preprocessing and clustering with Scanpy. Use for QC, normalization, HVG selection, PCA, neighbor graph construction, UMAP, Leiden clustering, and export of an analysis-ready AnnData object.

zongtingwei/Bioclaw_Skills_Hub · 51 tokens

alignment-and-mapping

Workflow for read alignment, sorting, indexing, mapping statistics, and downstream-ready alignment artifacts.

zongtingwei/Bioclaw_Skills_Hub · 23 tokens

machine-learning-for-omics

Workflow for predictive modeling, biomarker discovery, survival modeling, and explainability over omics-derived features.

zongtingwei/Bioclaw_Skills_Hub · 27 tokens