vllm-omni SKILL.md skillA

vllm-omni from air-gapped/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add air-gapped/skills/vllm-omni@git:20261018.81b7616

Pins git:20261018.81b7616 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/vllm-omni/SKILL.md
Versions recorded
11
Latest version
git:20261018.81b7616, committed Oct 18, 2026
First version recorded
Jun 7, 2026
Size
16,568 bytes
Repository stars
6
License
MIT

vLLM-Omni output-side multimodal generation — image (FLUX.1/2, Qwen-Image, GLM-Image, BAGEL, SD3.5, HunyuanImage-3.0), video (Wan2.1/2.2, LTX-2, HunyuanVideo-1.5), TTS (Qwen3-TTS, CosyVoice3, Voxtral-TTS), any-to-any omni (Qwen3-Omni, Qwen2.5-Omni, MiMo-Audio) via `vllm serve --omni`. Stage-based disaggregation (OmniConnector + Mooncake + RDMA), `/v1/images/generations`, async+sync `/v1/videos`, `/v1/audio/speech` with voice-upload, PCM16 WebSocket `/v1/realtime`, Ulysses/Ring SP +…

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-Omni — output-side multimodal serving

Target: operators who serve image / video / audio / any-to-any generation models with vLLM-Omni, a plugin layer on upstream vLLM. vllm-omni extends upstream vLLM (same CUDA/ROCm/NPU/XPU runtime, same OpenAI-compat API server) to add non-autoregressive DiT models, multi-stage pipeline execution, diffusion schedulers, CFG plumbing, and real-time streaming audio I/O — things upstream vLLM does not ship.

This skill is a **reference**, not a tutorial. SKILL.md holds the mental model, quick-answer router, top pitfalls, and operator cheat sheet. The `references/` files hold endpoint catalogs, supported-model tables, stage-config grammar, and the diffusion/DiT details. Read only the reference file that matches the question.

## How it plugs into vLLM
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add air-gapped/skills/vllm-omni@sha256:86adc8ec587aa990

The line at the top of this page pins the label git:20261018.81b7616, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_dygetrvwnokpzxmz.svg)](https://markdownregistry.com/a/art_dygetrvwnokpzxmz)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 11 versions of this file, between Jun 7, 2026 and Oct 18, 2026, about one every 13 days.

versioncommittedcommitsizeaudit
git:20261018.81b7616 latest2026-10-18 81b7616 16,568 BA view · diff
git:20261018.a862c982026-10-18 a862c98 17,214 BA view · diff
git:20261018.732124e2026-10-18 732124e 17,197 BA view · diff
git:20261018.228c37c2026-10-18 228c37c 18,016 BA view · diff
git:20261018.1350c932026-10-18 1350c93 18,009 BA view · diff
git:20260922.fd884232026-09-22 fd88423 19,714 BA view · diff
git:20260915.34767df2026-09-15 34767df 19,516 BA view · diff
git:20260818.36f64642026-08-18 36f6464 18,958 BA view · diff
git:20260811.5eae0c22026-08-11 5eae0c2 18,971 BA view · diff
git:20260721.5a247862026-07-21 5a24786 16,547 BA view · diff
git:20260607.aeb0bcc2026-06-07 aeb0bcc 13,120 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (16568 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

GitHub

air-gapped/skills · 6 stars · license MIT · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_dygetrvwnokpzxmz
GET https://markdownregistry.com/api/v1/resolve?ref=air-gapped/skills/vllm-omni
GET https://markdownregistry.com/api/v1/blob/86adc8ec587aa99073ca3cfc5234b2a318d6fb7b2303112b0986085b6c753c7a

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.

More from air-gapped/skills

aiperf SKILL.md skill
air-gapped/skills · .claude/skills/aiperf/SKILL.md · NVIDIA AIPerf — vendor-neutral generative-AI inference benchmarking (genai-perf successor). `aiperf profile`…
git:20261019.9eca78f · audit A · 6 stars
airgap-vetting SKILL.md skill
air-gapped/skills · .claude/skills/airgap-vetting/SKILL.md · Vet an open-source product for air-gap readiness BEFORE adoption. Answers eight questions — telemetry…
git:20261027.4b5fb58 · audit A · 6 stars
analytical-troubleshooting SKILL.md skill
air-gapped/skills · .claude/skills/analytical-troubleshooting/SKILL.md · Structured live troubleshooting for deviation problems: something worked (or should work) and now doesn't, and the…
git:20261019.819b406 · audit A · 6 stars
ansible-idrac-9-10 SKILL.md skill
air-gapped/skills · .claude/skills/ansible-idrac-9-10/SKILL.md · Run and debug `dellemc.openmanage` Ansible playbooks against Dell PowerEdge **iDRAC 9** (14G–16G) and **iDRAC 10** (17G…
git:20261019.b3bbe99 · audit A · 6 stars
argo-cd-apps SKILL.md skill
air-gapped/skills · .claude/skills/argo-cd-apps/SKILL.md · Author and maintain Argo CD `Application` and `ApplicationSet` manifests as a GitOps consumer (publisher), targeting…
git:20261027.31fbcc7 · audit A · 6 stars
autoresearch SKILL.md skill
air-gapped/skills · .claude/skills/autoresearch/SKILL.md · Autonomous experiment loops that hill-climb a measurable metric — apply one change, measure, keep it only if the number…
git:20261027.75d87c7 · audit A · 6 stars
baml-expert SKILL.md skill
air-gapped/skills · .claude/skills/baml-expert/SKILL.md · BAML (Boundary ML) expert for projects defining LLM calls as typed functions in .baml files with a generated Python…
git:20261027.db2bb25 · audit A · 6 stars
ceph-performance SKILL.md skill
air-gapped/skills · .claude/skills/ceph-performance/SKILL.md · Tune and benchmark a healthy Ceph cluster, with Rook-on-Kubernetes specifics: mClock profiles and the NVMe…
git:20261027.28d2580 · audit A · 6 stars
ceph-s3 SKILL.md skill
air-gapped/skills · .claude/skills/ceph-s3/SKILL.md · Run Ceph RGW as an S3 endpoint under Rook (CephObjectStore, CephObjectStoreUser, ObjectBucketClaim, COSI…
git:20261027.61472c6 · audit A · 6 stars
ceph-troubleshooting SKILL.md skill
air-gapped/skills · .claude/skills/ceph-troubleshooting/SKILL.md · Diagnose and recover an unhealthy Ceph cluster, with Rook-on-Kubernetes specifics: slow or stuck recovery/backfill…
git:20261027.0ad34cc · audit A · 6 stars
chat-completions-api SKILL.md skill
air-gapped/skills · .claude/skills/chat-completions-api/SKILL.md · Reference for the OpenAI Chat Completions API (/v1/chat/completions) and legacy /v1/completions as the lingua-franca…
git:20261027.42f4242 · audit A · 6 stars
claude-code-ci-harness SKILL.md skill
air-gapped/skills · .claude/skills/claude-code-ci-harness/SKILL.md · Run Claude Code headlessly as an isolated CI harness against any Anthropic Messages-compatible endpoint (local engine…
git:20261019.25dcc92 · audit A · 6 stars

Every file in air-gapped/skills

Browse by kind, by grade A, or by owner.