aiperf SKILL.md skillA
aiperf 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/aiperf@git:20261019.9eca78fPins git:20261019.9eca78f 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/aiperf/SKILL.md- Versions recorded
- 10
- Latest version
- git:20261019.2447ecd, committed Oct 19, 2026
- First version recorded
- Apr 25, 2026
- Size
- 21,926 bytes
- Repository stars
- 5
- License
- MIT
NVIDIA AIPerf — vendor-neutral generative-AI inference benchmarking (genai-perf successor). `aiperf profile`: concurrency / request-rate / fixed-schedule trace replay / user-centric / multi-run confidence, 19 endpoint types (chat, completions, embeddings, rankings, responses, messages, audio transcription, image-gen/edit, video-gen, NIM, HF-TGI, raw, template), 13 custom dataset formats (single/multi-turn; mooncake, bailian, burst_gpt, baseten, weka, tracelab traces; random_pool, dag_jsonl…
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
# AIPerf — NVIDIA generative-AI inference benchmarking Use for defensible latency / throughput / goodput numbers against any OpenAI-compatible server (vLLM, SGLang, TensorRT-LLM, NVIDIA Dynamo, NIM, Triton, HF TGI, Ollama), and for extending AIPerf with plugins. AIPerf is the `genai-perf` successor; its numbers differ for reasoning models (pitfall 2). For a vLLM-only target driven by the in-tree `vllm bench` toolchain, use the `vllm-benchmarking` skill; use AIPerf when the target is non-vLLM or the workload is trace-driven, multi-modal, multi-server, or needs goodput. ## Version-gated capabilities — check `aiperf --version` before using | Need | Use | Needs | |---|---|---| | Sweep or search instead of a shell loop | List flags (`--concurrency 10,50,100`), `--search-recipe <name>`, YAML `sweep:` / Bayesian search; multi-tier SLO search `--search-sla-tier` | recipes/BO v0.10.0; tiers v0.11.0 | | Several warmup/profiling phases, or adaptive scaling, in one run | Phases and scale variables in the YAML config | v0.12.0 | | Accuracy alongside perf | `--accuracy-benchmark` (see `references/cli.md`) | AIME v0.9.0; HellaSwag/BBH/AIME24-25 v0.10.0; MATH-500/GPQA/LCB/GSM8K v0.11.0 | …
Read the whole file at its exact version.
How to install
mdr add air-gapped/skills/aiperf@sha256:6f1646ab26b88521The line at the top of this page pins the label git:20261019.9eca78f, 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_a3qx4owokw3dupfk)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 10 versions of this file, between Apr 25, 2026 and Oct 19, 2026, about one every 20 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261019.2447ecd latest | 2026-10-19 | 2447ecd | 21,926 B | A | view · diff |
| git:20261019.292b9af | 2026-10-19 | 292b9af | 21,723 B | A | view · diff |
| git:20261019.6cdb9d7 | 2026-10-19 | 6cdb9d7 | 22,499 B | A | view · diff |
| git:20261019.9eca78f | 2026-10-19 | 9eca78f | 22,900 B | A | view · diff |
| git:20261019.b13b857 | 2026-10-19 | b13b857 | 22,803 B | A | view · diff |
| git:20260922.5e8f509 | 2026-09-22 | 5e8f509 | 19,764 B | A | view · diff |
| git:20260915.d674467 | 2026-09-15 | d674467 | 19,737 B | A | view · diff |
| git:20260721.6cc28be | 2026-07-21 | 6cc28be | 18,299 B | A | view · diff |
| git:20260529.3357782 | 2026-05-29 | 3357782 | 16,754 B | A | view · diff |
| git:20260425.9f338b0 | 2026-04-25 | 9f338b0 | 16,754 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 (21926 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 · 5 stars · license MIT · pushed 2026-10-28 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_a3qx4owokw3dupfk GET https://markdownregistry.com/api/v1/resolve?ref=air-gapped/skills/aiperf GET https://markdownregistry.com/api/v1/blob/6f1646ab26b88521504aa1fe3abe05420820f8e9539c47ed80f12bdb3880b6df
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.