vllm-caching SKILL.md skillA
vllm-caching 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-caching@git:20261027.b316b91Pins git:20261027.b316b91 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-caching/SKILL.md- Versions recorded
- 13
- Latest version
- git:20261027.b316b91, committed Oct 27, 2026
- First version recorded
- Sep 15, 2026
- Size
- 30,382 bytes
- Repository stars
- 6
- License
- MIT
vLLM tiered KV cache configuration for production H100/H200 clusters. Native CPU offload, LMCache (CPU+NVMe+GDS), NixlConnector (disaggregated prefill), MooncakeConnector (RDMA), MultiConnector composition. Version gates, sizing math (flag total across TP, not per-GPU — opposite of SGLang), KV-vs-weights offload distinction operators most often get wrong.
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 tiered KV caching Target audience: operators running vLLM on H100/H200-class datacenter GPUs in production. Assumes CUDA 12/13, Kubernetes or bare container deployment, multi-GPU tensor parallel. **Where this sits.** Cache flags are one slice of a serving config: the manifest that carries them (cache mounts, probes, image tags) is **`vllm-deployment`**, the non-cache throughput knobs are **`vllm-performance-tuning`**, and the numbers that justify either are **`vllm-benchmarking`** — all in the `vllm` plugin. For the same problem on other stacks, see **`sglang-hicache`** (SGLang's tiering) and **`lmcache-mp`** (LMCache as a standalone server rather than in-process). ## Version gates — check these FIRST Confirm the vLLM version before recommending any config. | Feature | First release | Notes | |---|---|---| | Native CPU KV offload (`vllm/v1/kv_offload/`) | **v0.11.0** (2025-10-02) | Infrastructure + scheduler integration | | CLI flags `--kv-offloading-size` / `--kv-offloading-backend` | **v0.11.1** (2025-11-18) | Before this, required editing config objects | …
Read the whole file at its exact version.
How to install
mdr add air-gapped/skills/vllm-caching@sha256:43e2382affe042a9The line at the top of this page pins the label git:20261027.b316b91, 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_xwbuqzst745b3uff)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 13 versions of this file, between Sep 15, 2026 and Oct 27, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261027.b316b91 latest | 2026-10-27 | b316b91 | 30,382 B | A | view · diff |
| git:20261018.d9125d4 | 2026-10-18 | d9125d4 | 30,314 B | A | view · diff |
| git:20261018.4ed4643 | 2026-10-18 | 4ed4643 | 29,779 B | A | view · diff |
| git:20261018.b4c73a9 | 2026-10-18 | b4c73a9 | 30,709 B | A | view · diff |
| git:20261018.892c19a | 2026-10-18 | 892c19a | 29,797 B | A | view · diff |
| git:20261018.86d4614 | 2026-10-18 | 86d4614 | 29,820 B | A | view · diff |
| git:20260923.466430c | 2026-09-23 | 466430c | 34,299 B | A | view · diff |
| git:20260922.fd88423 | 2026-09-22 | fd88423 | 32,450 B | A | view · diff |
| git:20260915.b479afb | 2026-09-15 | b479afb | 32,065 B | A | view · diff |
| git:20260915.58eb0a5 | 2026-09-15 | 58eb0a5 | 31,464 B | A | view · diff |
| git:20260915.b5aa18b | 2026-09-15 | b5aa18b | 31,030 B | A | view · diff |
| git:20260915.339f139 | 2026-09-15 | 339f139 | 30,732 B | A | view · diff |
| git:20260915.34651be | 2026-09-15 | 34651be | 29,941 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 (30382 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_xwbuqzst745b3uff GET https://markdownregistry.com/api/v1/resolve?ref=air-gapped/skills/vllm-caching GET https://markdownregistry.com/api/v1/blob/43e2382affe042a9ee2b49e3bced36a5b2aec3aefff4291b7b76a1a556fc4b20
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.