vllm-bench-serve

vllm-bench-serve is a skill for Claude Code from vllm-project/vllm-skills. It costs 93 tokens per session (1,958 once invoked), scanned A, original, Apache-2.0.

A benchmarking tool for vLLM or OpenAI-compatible model-serving endpoints. It sends controlled workloads and measures how quickly and steadily they handle requests.

In plain words
What is it for?
Use it to test throughput, latency, time to first token, time between output tokens, and goodput with supported datasets and backends, then save results.
Why use it?
It helps compare serving performance under different request loads instead of relying on guesses or single-request tests.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the vllm-skills plugin — 6 skills shipped together

Good fit Use it to test throughput, latency, time to first token, time between output tokens, and goodput with supported datasets and backends, then save results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vllm-project/vllm-skills/vllm-bench-serve
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 vllm-project/vllm-skills --skill vllm-bench-serve
Clone the repo
git clone --depth 1 https://github.com/vllm-project/vllm-skills

Made for: Claude Code.

Or install vllm-skills, the plugin that ships this one along with the rest of its 6 skills.

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-bench-serve

README.md
[![agentmods](https://agentmods.dev/badge/skills/vllm-project/vllm-skills/vllm-bench-serve/github.svg)](https://agentmods.dev/skills/vllm-project/vllm-skills/vllm-bench-serve)
Your own site
<a href="https://agentmods.dev/skills/vllm-project/vllm-skills/vllm-bench-serve"><img src="https://agentmods.dev/badge/skills/vllm-project/vllm-skills/vllm-bench-serve/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for vllm-bench-serve

Your own site · 80×15
<a href="https://agentmods.dev/skills/vllm-project/vllm-skills/vllm-bench-serve"><img src="https://agentmods.dev/badge/skills/vllm-project/vllm-skills/vllm-bench-serve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,958 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 $0.00093 $0.01958
Opus 5 $0.00046 $0.00979
Sonnet 5 $0.00019 $0.00392
Haiku 4.5 $0.00009 $0.00196

Measured 11d ago against content hash cb397fad2c5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

vllm-bench-serve 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 11d 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-skills/skills/vllm-bench-serve/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vLLM Bench Serve

Benchmark vLLM or any OpenAI-compatible serving endpoint using the vllm bench serve CLI. Measures throughput, latency (TTFT, TPOT), and goodput against configurable request load.

Reference: vLLM Bench Serve Documentation

Prerequisites

  • vLLM installed (or any OpenAI-compatible server running)
  • A vLLM server or API endpoint already serving a model
  • Python environment with vLLM for the benchmark client

Quick Start

Basic benchmark against local vLLM server (default random dataset, 1000 prompts):

vllm bench serve \
  --backend openai-chat \
  --host 127.0.0.1 \
  --port 8000 \
  --model Qwen/Qwen2.5-1.5B-Instruct \
  --endpoint /v1/chat/completions

Save results to JSON:

vllm bench serve \
  --backend openai-chat \
  --host 127.0.0.1 \
  --port 8000 \
  --model Qwen/Qwen2.5-1.5B-Instruct \
  --endpoint /v1/chat/completions \
  --save-result \
  --result-dir ./bench-results \
  --metadata "version=0.6.0" "tp=1"

Note: When using --backend openai-chat, you must specify --endpoint /v1/chat/completions (default is /v1/completions).

Core Arguments

Argument Default Description
--backend openai Backend type: openai, openai-chat, openai-embeddings, vllm, vllm-pooling, vllm-rerank, etc.
--host 127.0.0.1 Server host
--port 8000 Server port
--base-url - Alternative: full base URL instead of host:port
--endpoint /v1/completions API endpoint; use /v1/chat/completions for openai-chat
--model (from /v1/models) Model name
--num-prompts 1000 Number of prompts to process
--request-rate inf Requests per second; inf = burst all at once
--max-concurrency - Max concurrent requests (caps parallelism)
--num-warmups 0 Warmup requests before measuring

Datasets

--dataset-name Use Case
random Synthetic random prompts (default)
sharegpt ShareGPT conversation format; requires --dataset-path
sonnet Sonnet-style prompts
hf HuggingFace dataset; requires --dataset-path (dataset ID)
custom / custom_mm Custom dataset; requires --dataset-path
prefix_repetition Prefix repetition benchmark
random-mm Random multimodal (images/videos)
spec_bench Spec bench dataset

Read the full file on GitHub · 181 lines

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. 11d ago First seen · 181 lines · 93 tokens per session scan A cb397fad2c5e

Subscribe to this mod's changes

vllm-bench-serve is a skill published in the GitHub repository vllm-project/vllm-skills (98 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,958 once invoked, about $0.0005 per session on Opus 5. 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.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

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

NVIDIA/skills · 30 tokens