vllm-input-modalities SKILL.md skillA
vllm-input-modalities 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/vllm-input-modalities@git:20261018.ea0e0a5Pins git:20261018.ea0e0a5 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-input-modalities/SKILL.md- Versions recorded
- 11
- Latest version
- git:20261018.ea0e0a5, committed Oct 18, 2026
- First version recorded
- Apr 24, 2026
- Size
- 15,305 bytes
- Repository stars
- 6
- License
- MIT
vLLM non-chat inference surfaces — text embeddings (`/v1/embeddings`, `/v2/embed`), reranking/scoring (`/rerank`, `/score`), speech-to-text (`/v1/audio/transcriptions`, `/v1/audio/translations`), document OCR via VLMs. Covers 2026 `--runner pooling` (replacing `--task embed`), v0.20 deprecations (`score`→`classify`, multitask pooling, `encode`→`token_embed`+`token_classify`), Matryoshka/MRL, ColBERT/ColPali/ColQwen late-interaction MaxSim, Cohere v2 `/v2/embed`, Jina v3/v4/v5 quirks…
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 — embeddings, reranking, speech-to-text, OCR
Embedding and reranking run on the pooling runner; STT and OCR run on the
generate runner.
## The mental model — one flag rules the surface
vLLM decides what a model *does* from the combination of three flags:
```
--runner {auto|generate|pooling|draft} # what kind of workload
--convert {auto|none|embed|classify} # adapt a generative LM to a pooler
--pooler-config '{...}' # override pool type, dimensions, etc.
```
The pair `(runner, convert)` replaced `--task`, which no longer parses
(pitfall 1). Canonical today:
| Workload | Command | Runner | Notes |
|---|---|---|---|
| Chat / completion | `vllm serve <model>` | `generate` (auto) | default |
| Embedding | `vllm serve <model> --runner pooling` | `pooling` | auto-detects CLS/LAST/MEAN from config |
| Embedding from a causal LM | `vllm serve <model> --runner pooling --convert embed` | `pooling` | adapts `*ForCausalLM` checkpoints |
| Classification | `vllm serve <model> --runner pooling --convert classify` | `pooling` | also how `score`/`rerank` comes online |
…Read the whole file at its exact version.
How to install
mdr add air-gapped/skills/vllm-input-modalities@sha256:06dd171f43e466f4The line at the top of this page pins the label git:20261018.ea0e0a5, 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_aayfo53m6kiyjfyz)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 11 versions of this file, between Apr 24, 2026 and Oct 18, 2026, about one every 18 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261018.ea0e0a5 latest | 2026-10-18 | ea0e0a5 | 15,305 B | A | view · diff |
| git:20261018.ec82bf6 | 2026-10-18 | ec82bf6 | 15,554 B | A | view · diff |
| git:20261018.dae75ea | 2026-10-18 | dae75ea | 15,691 B | A | view · diff |
| git:20261018.1103dfe | 2026-10-18 | 1103dfe | 16,503 B | A | view · diff |
| git:20261018.eed9107 | 2026-10-18 | eed9107 | 17,381 B | A | view · diff |
| git:20260923.466430c | 2026-09-23 | 466430c | 23,974 B | A | view · diff |
| git:20260915.581525a | 2026-09-15 | 581525a | 21,894 B | A | view · diff |
| git:20260811.23dd79b | 2026-08-11 | 23dd79b | 21,646 B | A | view · diff |
| git:20260721.e38997a | 2026-07-21 | e38997a | 18,766 B | A | view · diff |
| git:20260529.785a0d2 | 2026-05-29 | 785a0d2 | 15,098 B | A | view · diff |
| git:20260424.4dca59c | 2026-04-24 | 4dca59c | 14,431 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 (15305 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_aayfo53m6kiyjfyz GET https://markdownregistry.com/api/v1/resolve?ref=air-gapped/skills/vllm-input-modalities GET https://markdownregistry.com/api/v1/blob/06dd171f43e466f42ef3ee13c51bf2693a2cf61e3bbcba8f217ebd13ee983967
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.