serving-llms-vllm SKILL.md skillA
serving-llms-vllm from orchestra-research/ai-research-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add orchestra-research/ai-research-skills/serving-llms-vllm@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- orchestra-research/ai-research-skills
- Path
12-inference-serving/vllm/SKILL.md- Versions recorded
- 5
- Latest version
- v1.0.0, committed Nov 20, 2025
- First version recorded
- Nov 7, 2025
- Size
- 9,026 bytes
- Repository stars
- 13,718
- License
- MIT
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.
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
# 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**:
```bash
pip install vllm
```
**Basic offline inference**:
```python
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**:
```bash
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
…Read the whole file at its exact version.
How to install
mdr add orchestra-research/ai-research-skills/serving-llms-vllm@sha256:57eaf97e982fe758The line at the top of this page pins the label v1.0.0, 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.
[](https://markdownregistry.com/a/art_zn4pn7dnikqrvet5)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Nov 7, 2025 and Nov 20, 2025, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2025-11-20 | 72c8b2c | 9,026 B | A | view · diff |
| v1.0.0 | 2025-11-20 | 51fc3a3 | 9,025 B | A | view · diff |
| v1.0.0 | 2025-11-20 | 81c38fe | 9,024 B | A | view · diff |
| v1.0.0 | 2025-11-19 | bd4461f | 9,023 B | A | view · diff |
| git:20251107.88351fe | 2025-11-07 | 88351fe | 8,786 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9026 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
orchestra-research/ai-research-skills · 13,718 stars · license MIT · pushed 2026-10-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_zn4pn7dnikqrvet5 GET https://markdownregistry.com/api/v1/resolve?ref=orchestra-research/ai-research-skills/serving-llms-vllm GET https://markdownregistry.com/api/v1/blob/57eaf97e982fe758b6fd0ef2281b6961940e4a1c8258f303b0ce02d55d0636c6
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.