vllm-benchmarking SKILL.md skillA
vllm-benchmarking 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-benchmarking@git:20261018.4bad7f5Pins git:20261018.4bad7f5 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-benchmarking/SKILL.md- Versions recorded
- 11
- Latest version
- git:20261018.4bad7f5, committed Oct 18, 2026
- First version recorded
- May 29, 2026
- Size
- 12,169 bytes
- Repository stars
- 6
- License
- MIT
Run production vLLM benchmarks — `vllm bench` (serve, throughput, latency, sweep, startup, mm-processor), request-rate vs max-concurrency semantics, TTFT/TPOT/ITL/E2EL percentiles, goodput SLO measurement, prefix-cache workloads, air-gapped operation (HF_ENDPOINT, ModelScope, hf-mirror, offline cache). Methodology split — SLO health checks vs A/B change sweeps — plus pitfalls that produce misleading numbers (no warmup, wrong tokenizer, random-as-prod, `--request-rate inf` alone).
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 benchmarking Target audience: operators producing defensible latency/throughput numbers against production or pre-production vLLM deployments, on datacenter GPUs, often in containerized or air-gapped environments. **This skill measures; it does not tune.** Once a number is trusted and the verdict is "too slow", the knobs live elsewhere in the `vllm` plugin: **`vllm-performance-tuning`** (scheduler, MoE kernels, CUDA graphs, parallelism), **`vllm-caching`** (KV tiering when the bottleneck is prefill or cache capacity), **`vllm-nvidia-hardware`** (the SKU's own ceiling). Measure → change one thing → re-measure with the same methodology; a tuning change compared against a differently-shaped benchmark run is not evidence. ## What a bad benchmark costs A wrong number is acted on with the same confidence as a right one. Three failure modes, by what they cause — the flags that produce each are in **Critical pitfalls** below: 1. **Wrong methodology** → GPUs bought to fix a latency problem, or a latency regression shipped because total throughput looked fine. 2. **Wrong workload** → caching wins that do not survive contact with production. …
Read the whole file at its exact version.
How to install
mdr add air-gapped/skills/vllm-benchmarking@sha256:7ef72166b5919c0aThe line at the top of this page pins the label git:20261018.4bad7f5, 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_bfh7rkqxdi66cm2l)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 11 versions of this file, between May 29, 2026 and Oct 18, 2026, about one every 14 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261018.4bad7f5 latest | 2026-10-18 | 4bad7f5 | 12,169 B | A | view · diff |
| git:20261018.11ca19f | 2026-10-18 | 11ca19f | 11,954 B | A | view · diff |
| git:20261018.1804f78 | 2026-10-18 | 1804f78 | 11,649 B | A | view · diff |
| git:20261018.c340e69 | 2026-10-18 | c340e69 | 11,430 B | A | view · diff |
| git:20261018.58382c1 | 2026-10-18 | 58382c1 | 11,360 B | A | view · diff |
| git:20260923.466430c | 2026-09-23 | 466430c | 12,108 B | A | view · diff |
| git:20260915.d1977c4 | 2026-09-15 | d1977c4 | 11,384 B | A | view · diff |
| git:20260811.02eea3a | 2026-08-11 | 02eea3a | 11,721 B | A | view · diff |
| git:20260725.aef8f18 | 2026-07-25 | aef8f18 | 11,386 B | A | view · diff |
| git:20260721.618717e | 2026-07-21 | 618717e | 10,867 B | A | view · diff |
| git:20260529.f15a2a5 | 2026-05-29 | f15a2a5 | 10,811 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 (12169 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_bfh7rkqxdi66cm2l GET https://markdownregistry.com/api/v1/resolve?ref=air-gapped/skills/vllm-benchmarking GET https://markdownregistry.com/api/v1/blob/7ef72166b5919c0aa689ba0f7a0f16c17b89c4cf9da2154623dd41e16a2db1de
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.