vllm-gemma-4-31b SKILL.md skillA
vllm-gemma-4-31b 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-gemma-4-31b@git:20261018.e3f43e6Pins git:20261018.e3f43e6 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-gemma-4-31b/SKILL.md- Versions recorded
- 12
- Latest version
- git:20261018.e3f43e6, committed Oct 18, 2026
- First version recorded
- Jul 21, 2026
- Size
- 20,575 bytes
- Repository stars
- 6
- License
- MIT
Operating-point reference for serving Gemma 4 31B on vLLM — TP sizing, max_model_len, max_num_seqs, gpu_memory_utilization, kv_cache_dtype, EAGLE3 spec-dec, chat_template choice.
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
# Gemma 4 31B on vLLM — operating-point reference **One model, measured.** This is a worked operating point, not the general method. The reusable machinery lives in the `vllm` plugin: flag and env semantics in **`vllm-configuration`**, the K8s/container manifest in **`vllm-deployment`**, reproducing or re-measuring these numbers in **`vllm-benchmarking`**, and the prompt-side template in **`vllm-chat-templates`**. Deploying a *different* model? Use those, not this. For platform engineers deploying `google/gemma-4-31B-it` (BF16, FP8) or its community quants (e.g. `cyankiwi/gemma-4-31B-it-AWQ-4bit`, `RedHatAI/*-Gemma-4-31B-*`) on vLLM 0.29.0+ (version floor below). Pulls together measurements from a 2× H100 SXM5 80GB (NVLink) audit on 2026-04-30 — **taken on vLLM 0.20.0 and not re-run since** (see `references/bench-numbers.md`; the shape of the curves has held, but treat the absolute figures as 0.20.0 observations) — and the upstream constraints that shape the answer. > **Version floor: run vLLM 0.29.0 or newer; 0.30.0+ is the production line.** > Do not pin 0.25.1 or older: they carry the `<turn|>` / `enable_thinking` …
Read the whole file at its exact version.
How to install
mdr add air-gapped/skills/vllm-gemma-4-31b@sha256:1b29324d4d78da2aThe line at the top of this page pins the label git:20261018.e3f43e6, 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_avf2ooxur6irdzks)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 12 versions of this file, between Jul 21, 2026 and Oct 18, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261018.e3f43e6 latest | 2026-10-18 | e3f43e6 | 20,575 B | A | view · diff |
| git:20261018.4e6579d | 2026-10-18 | 4e6579d | 21,084 B | A | view · diff |
| git:20261018.2a3cd6e | 2026-10-18 | 2a3cd6e | 20,840 B | A | view · diff |
| git:20261018.996b21b | 2026-10-18 | 996b21b | 20,816 B | A | view · diff |
| git:20261018.381977d | 2026-10-18 | 381977d | 22,744 B | A | view · diff |
| git:20260923.466430c | 2026-09-23 | 466430c | 27,735 B | A | view · diff |
| git:20260922.fd88423 | 2026-09-22 | fd88423 | 26,038 B | A | view · diff |
| git:20260811.5bb3517 | 2026-08-11 | 5bb3517 | 25,855 B | A | view · diff |
| git:20260802.08faa47 | 2026-08-02 | 08faa47 | 22,308 B | A | view · diff |
| git:20260802.c4bc43c | 2026-08-02 | c4bc43c | 21,217 B | A | view · diff |
| git:20260725.aef8f18 | 2026-07-25 | aef8f18 | 14,988 B | A | view · diff |
| git:20260721.6b9197a | 2026-07-21 | 6b9197a | 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 (20575 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_avf2ooxur6irdzks GET https://markdownregistry.com/api/v1/resolve?ref=air-gapped/skills/vllm-gemma-4-31b GET https://markdownregistry.com/api/v1/blob/1b29324d4d78da2a3c79d3d45cee1a5804ab7a44c531ee7d2af803bfaa6d07a1
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.