vllm-configuration SKILL.md skillA
vllm-configuration from air-gapped/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add air-gapped/skills/vllm-configuration@git:20261018.f0e950aPins git:20261018.f0e950a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- air-gapped/skills
- Path
.claude/skills/vllm-configuration/SKILL.md- Versions recorded
- 12
- Latest version
- git:20261018.f0e950a, committed Oct 18, 2026
- First version recorded
- Sep 15, 2026
- Size
- 14,043 bytes
- Repository stars
- 6
- License
- MIT
Configure vLLM completely — YAML config file format, CLI arg precedence, full VLLM_*/HF_*/TRANSFORMERS_* env-var catalog, end-to-end recipe for air-gapped environments (internal HF mirrors, hf-mirror.com, ModelScope, HF_HUB_OFFLINE with pre-seeded cache, gated models offline, trust_remote_code supply-chain implications). VLLM_HOST_IP vs API-host confusion, Kubernetes-service-named-`vllm` env-var poisoning, usage-stats triple opt-out, YAML precedence surprises.
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 configuration Target audience: operators deploying vLLM in production — datacenter GPUs, containerized, often inside networks that can't reach `huggingface.co` directly and need to use internal mirrors or fully offline caches. ## Precedence, in one sentence **CLI arg > `--config FILE.yaml` > `VLLM_*` env var > library default.** So `vllm serve /models/llama --config prod.yaml` uses `/models/llama` even if `prod.yaml` sets `model: meta-llama/Llama-3.1-8B`. And `VLLM_LOGGING_LEVEL=DEBUG` is overridden by `--log-level=INFO`. One non-obvious case: env vars that *vLLM reads directly* (like `HF_HUB_OFFLINE`) are consumed by the library layer, not the arg parser, so they aren't subject to this precedence — they gate behaviour unconditionally. ## The YAML config file Every CLI flag has a YAML equivalent. Keys use the same name, hyphens allowed or underscored. Booleans must be explicit (`true`/`false`, not YAML's loose `yes`/`on`). ```yaml # prod.yaml model: /mnt/models/Llama-3.1-70B-Instruct tensor-parallel-size: 4 gpu-memory-utilization: 0.9 max-model-len: 32768 dtype: bfloat16 enable-prefix-caching: true served-model-name: llama-70b …
Read the whole file at its exact version.
How to install
mdr add air-gapped/skills/vllm-configuration@sha256:c501a2f11a2e52e4The line at the top of this page pins the label git:20261018.f0e950a, 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_tnukbqju67qbsvl5)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 12 versions of this file, between Sep 15, 2026 and Oct 18, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261018.f0e950a latest | 2026-10-18 | f0e950a | 14,043 B | A | view · diff |
| git:20261018.80e0230 | 2026-10-18 | 80e0230 | 14,247 B | A | view · diff |
| git:20261018.c3e18ab | 2026-10-18 | c3e18ab | 14,236 B | A | view · diff |
| git:20261018.656120a | 2026-10-18 | 656120a | 14,776 B | A | view · diff |
| git:20261018.bd60686 | 2026-10-18 | bd60686 | 14,559 B | A | view · diff |
| git:20260923.466430c | 2026-09-23 | 466430c | 20,875 B | A | view · diff |
| git:20260922.fd88423 | 2026-09-22 | fd88423 | 19,740 B | A | view · diff |
| git:20260915.d6039bf | 2026-09-15 | d6039bf | 19,375 B | A | view · diff |
| git:20260915.81165ec | 2026-09-15 | 81165ec | 18,967 B | A | view · diff |
| git:20260915.70fb0c1 | 2026-09-15 | 70fb0c1 | 17,927 B | A | view · diff |
| git:20260915.3c4dc21 | 2026-09-15 | 3c4dc21 | 16,025 B | A | view · diff |
| git:20260915.9e1fc69 | 2026-09-15 | 9e1fc69 | 14,566 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 (14043 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
air-gapped/skills · 6 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_tnukbqju67qbsvl5 GET https://markdownregistry.com/api/v1/resolve?ref=air-gapped/skills/vllm-configuration GET https://markdownregistry.com/api/v1/blob/c501a2f11a2e52e4f1fc95f4055d61f06ccd0664dff802d794388ad3a1fbdab1
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.