sglang-xpu-run SKILL.md skillB
sglang-xpu-run 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/sglang-xpu-run@git:20261013.3c08426Pins git:20261013.3c08426 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- intel/skills
- Path
skills/sglang-xpu-run/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261013.3c08426, committed Oct 13, 2026
- First version recorded
- Sep 3, 2026
- Size
- 24,893 bytes
- Repository stars
- 29
- License
- Apache-2.0
Serve a Hugging Face safetensors model on an Intel GPU using SGLang's XPU backend with the OpenAI-compatible API. Covers pulling the official `lmsysorg/sglang:v0.5.20-xpu` release image, the container flag set for Intel DRM devices, the UMD/kernel pairing the image pins, the `--device xpu --attention-backend intel_xpu` flag set, page-size and quantization constraints, multimodal serving, and how to validate output content (not just HTTP 200). Use when the user needs SGLang's RadixAttention…
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
# sglang-xpu-run
SGLang's XPU backend is functional and ships as an official release image:
`lmsysorg/sglang:v0.5.20-xpu`. Verify GPU detection before serving; SGLang
silently falls back to CPU and you'll only notice when throughput is 50×
lower than expected.
If you don't specifically need RadixAttention prefix caching or
grammar-constrained output, prefer **vllm-xpu-run** — its Intel coverage
is broader today.
## Step 0 — discover GPUs and host RAM before anything else
Run **xpu-discover** first, or at minimum:
```sh
# GPU inventory
xpu-smi discovery
# Count cards and host RAM — used to size ZE_AFFINITY_MASK and --tp
GPU_COUNT=$(xpu-smi discovery 2>/dev/null | grep -cE "^\| +[0-9]|Device [0-9]+:")
[ "${GPU_COUNT:-0}" -gt 0 ] || GPU_COUNT=1
RAM_GB=$(awk '/MemTotal/{print int($2/1024/1024)}' /proc/meminfo)
RENDER_GID=$(getent group render 2>/dev/null | cut -d: -f3)
RENDER_GID=${RENDER_GID:-$(stat -c '%g' /dev/dri/renderD128 2>/dev/null)}
echo "GPUs: $GPU_COUNT RAM: ${RAM_GB} GB render GID: $RENDER_GID"
```
Use `GPU_COUNT` to set `ZE_AFFINITY_MASK` and `--tp`; use `RENDER_GID` in
every `docker run` command below.
## CUDA → XPU cheat sheet
| CUDA | Intel |
|---|---|
…Read the whole file at its exact version.
How to install
mdr add intel/skills/sglang-xpu-run@sha256:0a6b448c8d05ff4dThe line at the top of this page pins the label git:20261013.3c08426, 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_qms5xf4l566yalnq)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 3, 2026 and Oct 13, 2026, about one every 40 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261013.3c08426 latest | 2026-10-13 | 3c08426 | 24,893 B | B | view · diff |
| git:20260903.b1ad034 | 2026-09-03 | b1ad034 | 13,871 B | B | view |
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (24893 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_qms5xf4l566yalnq GET https://markdownregistry.com/api/v1/resolve?ref=intel/skills/sglang-xpu-run GET https://markdownregistry.com/api/v1/blob/0a6b448c8d05ff4d62b4bef7909291d65d6a6e81bb8d7650d0be046a9b88862a
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.