vllm SKILL.md skillA

vllm from znlgis/opengis-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add znlgis/opengis-skills/vllm@git:20261027.8e03282

Pins git:20261027.8e03282 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
znlgis/opengis-skills
Path
ai/vllm/SKILL.md
Versions recorded
1
Latest version
git:20261027.8e03282, committed Oct 27, 2026
Size
13,760 bytes
Repository stars
78
License
MIT

Use when self-hosting an OpenAI-compatible LLM endpoint with vLLM 0.32 — vllm serve, offline LLM.generate / llm.chat, PagedAttention with continuous batching and prefix caching, --tensor-parallel-size / --pipeline-parallel-size, AWQ/GPTQ/FP8 quantization, or wiring LangChain/LlamaIndex clients at http://localhost:8000/v1; also when the server OOMs on long context, chat requests ignore your sampling params because generation_config.json overrides them, or engine startup dies compiling kernels.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

> **项目地址:** <https://github.com/vllm-project/vllm>
>
> **官方文档:** <https://docs.vllm.ai/>
>
> **PyPI:** `vllm`(0.32.0,截至 2026-10)
>
> **许可证:** Apache-2.0

## 概述

vLLM 是目前最主流的开源 LLM 推理与服务平台,把"高吞吐、低延迟、OpenAI 兼容"三件事一次做掉。

- **PagedAttention**:KV cache 按页管理,显存碎片少、并发高
- **Continuous batching / chunked prefill / prefix caching**:连续批处理、分块预填充、前缀复用
- **量化**:FP8、MXFP8/MXFP4、NVFP4、INT8、INT4、GPTQ/AWQ、GGUF、compressed-tensors、ModelOpt、TorchAO 等
- **并行**:tensor / pipeline / data / expert / context 并行,支持多机
- **OpenAI 兼容 API**:`/v1/models`、`/v1/completions`、`/v1/chat/completions`,另支持 Anthropic Messages API 与 gRPC
- **模型面广**:200+ Hugging Face 架构(Llama / Qwen / Gemma / Mixtral / DeepSeek-V3 / Qwen-MoE / GPT-OSS / Mamba / 多模态 / embedding / reward)
- **硬件**:NVIDIA、AMD、Intel GPU,x86/ARM/PowerPC CPU,以及 TPU / Gaudi / Ascend 等插件

---

## 环境准备

### 前置条件

| 项 | 要求 |
|----|------|
| 操作系统 | Linux(macOS 需走 vLLM-Metal;Windows 建议 WSL2 + Linux 容器) |
| Python | 3.11 – 3.14 |
| GPU | NVIDIA 需匹配的 CUDA 驱动;AMD 走 ROCm wheel;Intel 走 XPU |
| 磁盘 | 模型权重 + 编译产物,几十 GB 起步 |

### 方式一:uv(官方推荐)

```bash
uv venv --python 3.12 --seed
source .venv/bin/activate
uv pip install vllm --torch-backend=auto
vllm download-kernels
```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add znlgis/opengis-skills/vllm@sha256:994628e3ee1dd876

The line at the top of this page pins the label git:20261027.8e03282, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_sjlu5jxg3mx4ock7.svg)](https://markdownregistry.com/a/art_sjlu5jxg3mx4ock7)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 27, 2026.

versioncommittedcommitsizeaudit
git:20261027.8e03282 latest2026-10-27 8e03282 13,760 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (13760 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

znlgis/opengis-skills · 78 stars · license MIT · pushed 2026-10-27 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_sjlu5jxg3mx4ock7
GET https://markdownregistry.com/api/v1/resolve?ref=znlgis/opengis-skills/vllm
GET https://markdownregistry.com/api/v1/blob/994628e3ee1dd876f7bcd496b28eb5019c8549002db129e372435da6c33f041f

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from znlgis/opengis-skills

3d-skills SKILL.md skill
znlgis/opengis-skills · 3d/SKILL.md · Use when working with 3D Gaussian Splatting (3DGS), .ply model cleanup/compression/publishing, interactive 360-degree…
git:20261027.8e03282 · audit A · 78 stars
ara3d-sdk SKILL.md skill
znlgis/opengis-skills · 3d/ara3d-sdk/SKILL.md · Use when processing AEC/BIM 3D data in .NET 8 — mesh generation and transformation, SIMD-accelerated math, IFC/STEP/PLY…
git:20261027.8e03282 · audit A · 78 stars
elements SKILL.md skill
znlgis/opengis-skills · 3d/elements/SKILL.md · Use when generating building information models (BIM) programmatically in C#/.NET — wall, beam, column, floor creation…
git:20261027.8e03282 · audit A · 78 stars
open3d SKILL.md skill
znlgis/opengis-skills · 3d/open3d/SKILL.md · Use when processing 3D point clouds and meshes in Python — read/write PLY/PCD, voxel downsample, normal estimation…
git:20261027.8e03282 · audit A · 78 stars
opencsg-net SKILL.md skill
znlgis/opengis-skills · 3d/opencsg-net/SKILL.md · Use when doing constructive solid geometry (CSG) modeling in .NET — cube/sphere/cylinder primitives…
git:20261015.5d0de0d · audit A · 78 stars
photo-sphere-viewer SKILL.md skill
znlgis/opengis-skills · 3d/photo-sphere-viewer/SKILL.md · Use when displaying 360-degree panoramic images (equirectangular/cubemap/dual-fisheye) in web applications, building…
git:20261027.8e03282 · audit B · 78 stars
supersplat SKILL.md skill
znlgis/opengis-skills · 3d/supersplat/SKILL.md · Use when editing 3D Gaussian Splatting (3DGS) .ply models in browser — cleanup noise/floaters, crop, transform…
git:20261027.8e03282 · audit A · 78 stars
opengis-skills SKILL.md skill
znlgis/opengis-skills · SKILL.md · Use when AI coding assistant needs GIS/CAD/C#/AI/IoT/3D domain expertise. Index of 114 skills across 8 categories: gis…
git:20261027.6562616 · audit A · 78 stars
ai-skills SKILL.md skill
znlgis/opengis-skills · ai/SKILL.md · Use when building LLM applications, RAG knowledge bases, AI agents, multi-agent crews, high-throughput model serving…
git:20261027.8e03282 · audit A · 78 stars
crewai SKILL.md skill
znlgis/opengis-skills · ai/crewai/SKILL.md · Use when orchestrating multi-agent work with crewAI 1.15 — Agent/Task/Crew, Process.sequential vs hierarchical, @tool /…
git:20261027.8e03282 · audit B · 78 stars
deepseek-harness SKILL.md skill
znlgis/opengis-skills · ai/deepseek-harness/SKILL.md · Use when running, scripting, or extending DeepSeek Harness (dsh) 0.2.1 — npx @deepseek-ai/dsh web / dsh --profile…
git:20261027.8e03282 · audit B · 78 stars
dify SKILL.md skill
znlgis/opengis-skills · ai/dify/SKILL.md · Use when self-hosting an LLM app platform with visual orchestration — docker compose up in dify/docker, knowledge bases…
git:20261027.8e03282 · audit A · 78 stars

Every file in znlgis/opengis-skills

Other files named vllm

vllm SKILL.md skill
magnus919/agent-skills · vllm/SKILL.md · Operate, configure, benchmark, and troubleshoot vLLM inference servers: Docker and Kubernetes deployment…
git:20260803.6181f17 · audit C · 166 stars

Browse by kind, by grade A, or by owner.