vllm-xpu-bench SKILL.md skillB
vllm-xpu-bench from intel/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add intel/skills/vllm-xpu-bench@git:20261105.c8947acPins git:20261105.c8947ac in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- intel/skills
- Path
skills/vllm-xpu-bench/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261105.c8947ac, committed Nov 5, 2026
- First version recorded
- Sep 3, 2026
- Size
- 11,829 bytes
- Repository stars
- 29
- License
- Apache-2.0
Benchmark a **running vLLM-XPU OpenAI-compatible server** on an Intel GPU using `vllm bench`. Measures TTFT (time-to-first-token), TPOT (time-per-output-token), ITL (inter-token latency), end-to-end latency, and throughput under concurrency. Covers online (`vllm bench serve`) and offline (`vllm bench throughput`) modes; concurrency sweeps and quant comparison live in `references/sweep-and-compare.md`. Use after **vllm-xpu-run** when the user asks "how fast is this?".
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-xpu-bench
`vllm bench` is the same CLI on Intel as on CUDA. The XPU-specific
levers are the serve-side flags from **vllm-xpu-run**
(`--max-model-len`, `--gpu-memory-utilization`, `--block-size=64`).
Pure measurement; for fixes see profiling skills.
Leave XPU graphs on when benchmarking v0.31.0+ images: adding
`--enforce-eager` roughly halves decode throughput (measured TPOT
64 ms vs 36 ms), so an eager baseline understates what the deployment
will actually do.
## Preflight — find the container and verify the server
Before benchmarking, identify the running vLLM container. The bench
client **must always run inside the container via `docker exec`** —
never on the host. This shares the engine's network namespace and
reuses the already-loaded tokenizer cache.
### 1. Find the vLLM container name
```sh
docker ps --format 'table {{.Names}}\t{{.Image}}\t{{.Ports}}\t{{.Status}}' | grep -iE 'vllm|8000'
```
This gives you `<container-name>`. If multiple containers appear, ask
the user which one to bench. **Do not proceed without a confirmed
container name.**
### 2. Verify the API is reachable and confirm the server is vLLM
```sh
…Read the whole file at its exact version.
How to install
mdr add intel/skills/vllm-xpu-bench@sha256:efa39f67d9d5959dThe line at the top of this page pins the label git:20261105.c8947ac, 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_ydwxlbzojh77rfzp)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Sep 3, 2026 and Nov 5, 2026, about one every 32 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261105.c8947ac latest | 2026-11-05 | c8947ac | 11,829 B | B | view · diff |
| git:20260924.04b65aa | 2026-09-24 | 04b65aa | 11,683 B | B | view · diff |
| git:20260903.b1ad034 | 2026-09-03 | b1ad034 | 11,729 B | B | view |
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1:8000)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11829 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 script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
intel/skills · 29 stars · license Apache-2.0 · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ydwxlbzojh77rfzp GET https://markdownregistry.com/api/v1/resolve?ref=intel/skills/vllm-xpu-bench GET https://markdownregistry.com/api/v1/blob/efa39f67d9d5959d5278efd3f9ee1e253311a64532c3b86c0b1948e1bc621157
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.