model-config-recommend SKILL.md skillA
model-config-recommend 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/model-config-recommend@git:20261105.82818bdPins git:20261105.82818bd in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- intel/skills
- Path
skills/model-config-recommend/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261105.82818bd, committed Nov 5, 2026
- First version recorded
- Sep 3, 2026
- Size
- 14,793 bytes
- Repository stars
- 29
- License
- Apache-2.0
Recommend how to configure vLLM-XPU for a Hugging Face decoder-only LLM on Intel Arc B-series GPUs: choose quantization, KV dtype, DP/TP layout, max concurrency, and max context using roofline math against published hardware specs. Use when the user asks "How should I configure vLLM?", requests the best vLLM configuration, or asks how to use one or multiple Arc cards. Must run recommend.py; predictions are physics-bounded ranges, not measured throughput. Use after xpu-discover and before…
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
# model-config-recommend **Status: experimental.** Emits physics-bounded predictions, not measurements. Scoped to **vLLM-XPU**; for SGLang use **model-can-it-fit** + **sglang-xpu-run** + **sglang-xpu-bench**. ## When to use The user has chosen an HF decoder-only LLM and wants to know which vLLM-XPU config (quant, KV dtype, DP/TP, max concurrency, max context) to start with on Intel Arc B-series. Broad wording such as "How should I configure vLLM for this model on my Arc cards?" still activates this skill because it requires selecting layout and deployment parameters rather than merely launching a server. Skip when: - Exact throughput numbers required -> use **vllm-xpu-bench**. - VLM or diffusion model -> use **model-can-it-fit**. - Hardware not in `data/hardware.json` (other Intel families). - MoE expert parallelism or speculative-decoding speedup — both workload-specific; the skill flags them as bench-only. ## Mandatory output contract (read first) Every recommendation answer MUST do all three, even when the model fits on one GPU — there is no "it's small, skip this" exception: 1. **Run `recommend.py`** this session against the user's actual …
Read the whole file at its exact version.
How to install
mdr add intel/skills/model-config-recommend@sha256:847c94555dd47c62The line at the top of this page pins the label git:20261105.82818bd, 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_raflly4qfejflsp5)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Sep 3, 2026 and Nov 5, 2026, about one every 21 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261105.82818bd latest | 2026-11-05 | 82818bd | 14,793 B | A | view · diff |
| git:20260930.057cd10 | 2026-09-30 | 057cd10 | 12,875 B | A | view · diff |
| git:20260924.04b65aa | 2026-09-24 | 04b65aa | 12,873 B | A | view · diff |
| git:20260903.b1ad034 | 2026-09-03 | b1ad034 | 12,489 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 (14793 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
intel/skills · 29 stars · license Apache-2.0 · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_raflly4qfejflsp5 GET https://markdownregistry.com/api/v1/resolve?ref=intel/skills/model-config-recommend GET https://markdownregistry.com/api/v1/blob/847c94555dd47c620c95b899a5f6abc7c32011ed4ea1f6674b04f4c5bd61049b
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.