sglang-model-gateway SKILL.md skillA
sglang-model-gateway 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/sglang-model-gateway@git:20261027.553c68dPins git:20261027.553c68d 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/sglang-model-gateway/SKILL.md- Versions recorded
- 10
- Latest version
- git:20261027.085e75a, committed Oct 27, 2026
- First version recorded
- Jul 21, 2026
- Size
- 28,823 bytes
- Repository stars
- 6
- License
- MIT
SGLang Model Gateway (`sgl-model-gateway`, formerly `sgl-router`) — Rust router fronting vLLM and SGLang inference workers on Kubernetes. Covers first-class vLLM gRPC backend plus HTTP transparent-proxy for vanilla vLLM, the policy set (6-8 `--policy` values by entrypoint, `cache_aware` default), tokenizer-format dispatch (`tokenizer.json` HF-fast vs `tiktoken.model` BPE — including when neither is required because `cache_aware` is text-based), air-gapped recipe…
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 Model Gateway — sgl-model-gateway Target audience: operators running **vLLM and/or SGLang inference on Kubernetes**, fronting workers with a router that does cache-aware load-balancing, optional prefill-decode disaggregation, and dynamic worker registration. Especially: hosting **multiple replicas of the same model** behind one address, in **air-gapped clusters with local model mirrors** (no live `huggingface.co`). ## Why this matters A single vLLM or SGLang process serves one Pod. To scale beyond one GPU, operators either fan-out replicas (N Pods, one Service) or run engine-internal data-parallelism (`vllm serve --data-parallel-size N`). Plain Kubernetes `Service` round-robins requests, which **fragments per-replica prefix caches** — every replica builds its own copy of the same prefix and hit rate divides by ~N. The Model Gateway is a Rust router that recovers most of that with a **cache-aware policy** (steers same-prefix requests to the same replica), adds health checks / circuit breakers / retries, exposes a unified OpenAI-compatible endpoint regardless of backend, and integrates with Kubernetes service discovery via label selectors. It also handles prefill-decode… …
Read the whole file at its exact version.
How to install
mdr add air-gapped/skills/sglang-model-gateway@sha256:ee06fad8ce86789fThe line at the top of this page pins the label git:20261027.553c68d, 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_3yb53rr6m4grxiij)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 10 versions of this file, between Jul 21, 2026 and Oct 27, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261027.085e75a latest | 2026-10-27 | 085e75a | 28,823 B | A | view · diff |
| git:20261027.41be0c8 | 2026-10-27 | 41be0c8 | 28,886 B | A | view · diff |
| git:20261027.553c68d | 2026-10-27 | 553c68d | 28,900 B | A | view · diff |
| git:20261027.724b7d5 | 2026-10-27 | 724b7d5 | 28,997 B | A | view · diff |
| git:20261027.f28b4e8 | 2026-10-27 | f28b4e8 | 28,972 B | A | view · diff |
| git:20260915.30751ed | 2026-09-15 | 30751ed | 29,287 B | A | view · diff |
| git:20260915.89838aa | 2026-09-15 | 89838aa | 28,957 B | A | view · diff |
| git:20260819.d6ab0ca | 2026-08-19 | d6ab0ca | 27,394 B | A | view · diff |
| git:20260721.f1a2db0 | 2026-07-21 | f1a2db0 | 25,827 B | A | view · diff |
| git:20260721.77070b3 | 2026-07-21 | 77070b3 | 25,044 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 (28823 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_3yb53rr6m4grxiij GET https://markdownregistry.com/api/v1/resolve?ref=air-gapped/skills/sglang-model-gateway GET https://markdownregistry.com/api/v1/blob/ee06fad8ce86789fee52cbd43c390b41c2e668e72c398846718d3da8de0fcf66
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.