vllm-chat-templates SKILL.md skillA

vllm-chat-templates 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-chat-templates@git:20261018.35a61a4

Pins git:20261018.35a61a4 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-chat-templates/SKILL.md
Versions recorded
12
Latest version
git:20261018.35a61a4, committed Oct 18, 2026
First version recorded
Apr 24, 2026
Size
24,942 bytes
Repository stars
6
License
MIT

vLLM chat-template (prompt-side Jinja) operator reference. Template resolution precedence (`--chat-template` → AutoProcessor → tokenizer default → bundled fallback), `chat_template_kwargs` allowlist silently dropping `add_generation_prompt`/`enable_thinking`/custom kwargs (PR 27622 fix), 27 shipped `tool_chat_template_*.jinja` files, known template-layer bugs for Qwen3/Qwen3-Coder, DeepSeek-R1/V3/V3.1/V3.2, GPT-OSS, Kimi-K2, Llama-4, Mistral (HF vs mistral mode), Gemma-3/4, Phi-4, GLM. Prompt…

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 chat templates — operator triage

Target audience: operators deploying vLLM in production. Assumes OpenAI-API-compatible frontend (`/v1/chat/completions` or `/v1/responses`), multi-GPU, mid-2024 through 2026 model families.

## Scope — three sibling skills, three layers

Chat-template bugs span three layers. This skill owns the **prompt-rendering** layer; route to a sibling when the problem is output-side.

| Layer | Direction | Skill | What it covers |
|---|---|---|---|
| **Chat template (Jinja)** | messages → prompt string | **this skill** | template precedence, `--chat-template`, `chat_template_kwargs`, `examples/tool_chat_template_*.jinja`, bundled fallbacks |
| **Reasoning parser** | model output → `reasoning_content` + `content` | `vllm-reasoning-parsers` | `--reasoning-parser`, `extract_reasoning`, `is_reasoning_end`, `<think>` splitting |
| **Tool parser** | model output → `tool_calls[]` | `vllm-tool-parsers` | `--tool-call-parser`, streaming state machines, partial-JSON parsing |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add air-gapped/skills/vllm-chat-templates@sha256:b6927979020340ca

The line at the top of this page pins the label git:20261018.35a61a4, 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_yrbv53idz6tk6pnd.svg)](https://markdownregistry.com/a/art_yrbv53idz6tk6pnd)

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

Versions

The registry has recorded 12 versions of this file, between Apr 24, 2026 and Oct 18, 2026, about one every 16 days.

versioncommittedcommitsizeaudit
git:20261018.35a61a4 latest2026-10-18 35a61a4 24,942 BA view · diff
git:20261018.c7a89b82026-10-18 c7a89b8 25,234 BA view · diff
git:20261018.722690d2026-10-18 722690d 25,166 BA view · diff
git:20261018.1ee6a202026-10-18 1ee6a20 25,799 BA view · diff
git:20261018.964ad7d2026-10-18 964ad7d 26,241 BA view · diff
git:20260923.466430c2026-09-23 466430c 24,600 BA view · diff
git:20260922.fd884232026-09-22 fd88423 22,986 BA view · diff
git:20260915.517712e2026-09-15 517712e 22,997 BA view · diff
git:20260811.74582f82026-08-11 74582f8 22,357 BA view · diff
git:20260721.b2cb5df2026-07-21 b2cb5df 20,014 BA view · diff
git:20260529.dbe2d452026-05-29 dbe2d45 19,508 BA view · diff
git:20260424.4dca59c2026-04-24 4dca59c 19,434 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 (24942 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_yrbv53idz6tk6pnd
GET https://markdownregistry.com/api/v1/resolve?ref=air-gapped/skills/vllm-chat-templates
GET https://markdownregistry.com/api/v1/blob/b6927979020340caa377515acc6886baee5b557065703fc13eb0803f6146ae4a

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.