[BwL1289]

Summary

This pull request adds the vLLM Ray Inference Server pattern to the site in the sandbox tier.

The pattern deploys an OpenAI-compatible LLM server on one OpenShift cluster. One pod runs Ray Serve LLM with the vLLM engine on one NVIDIA GPU. The cluster builds the server image with a BuildConfig from hash-pinned PyPI wheels on the NVIDIA CUDA UBI 9 image. OpenShift GitOps deploys the server, the NVIDIA GPU Operator and Node Feature Discovery, Vault with the External Secrets Operator for an optional Hugging Face token, and a JupyterLab notebook that times the server.

• Pattern repository: https://github.com/eugo-inc/rhvp-vllm-ray-inference-server
• Tier: sandbox (tier: sandbox, validated: false)
• Support: community best effort through the pattern's GitHub issues. Red Hat does not support the pattern.

We also emailed hybrid-cloud-patterns@googlegroups.com on 2026-11-08 to ask for the informal technical and
architecture reviews that the sandbox tier asks for. If that list is no longer read, or if it is easier, this pull
request can carry those reviews.

Files

File	What it is
content/patterns/rhvp-vllm-ray-inference-server/_index.adoc	Overview: background, architecture, deployed components, the AWS cost warning, and the support statement
content/patterns/rhvp-vllm-ray-inference-server/getting-started.adoc	Prerequisites, installation, a test request, the notebook, and uninstallation, including deleting the GPU machine set
static/images/rhvp-vllm-ray-inference-server/architecture.svg	Architecture diagram, rendered from the Mermaid source in the pattern README

Sandbox tier requirements

Requirement	Status
Implementation requirements	The pattern uses the clustergroup chart, the Validated Patterns Operator, and idempotent imperative jobs stored in Git. Its repository is public.
Deploys onto a freshly deployed OpenShift cluster without modification	A fresh install passed: ./pattern.sh make install from main at 1a781d1, with default settings, on a new installer-provisioned AWS cluster (OpenShift 4.22.18, us-east-1, three m5.2xlarge nodes, no cluster changes). The command's own Argo CD health check passed, with all seven Argo CD applications Synced and Healthy. The pattern added the GPU node, the cluster built both images, the server answered the OpenAI API, and the notebook ran against it with no errors. An earlier install, on another new AWS cluster, found one bug (OpenShift's builder records an empty CMD as /bin/sh -c null), which 1a781d1 fixes (README, What this pattern was verified against).
README states the business problem	README, "The problem it solves"
pattern-metadata.yaml	pattern-metadata.yaml
Architecture drawing	README, Architecture, and architecture.svg in this pull request
Informal technical review	Requested by email to the mailing list on 2026-11-08, or here
Informal architecture review	Requested by email to the mailing list on 2026-11-08, or here
Support policy	README, Support, and the Support section of _index.adoc

Notes for reviewers

• The name can change. The directory, aliases, image folder, and links use the current repository name. Two
  questions are open with the Validated Patterns team: whether the rhvp- prefix is acceptable under the Red Hat
  trademark guidelines, and whether the repository moves to validatedpatterns-sandbox. A comment at the top of the
  front matter says which values to change together.
• No partners entry. The pattern uses NVIDIA, Ray, and vLLM software, but no partner organization takes part in
  it. The front matter explains this in a comment. Leaving the field out also keeps the partner trademark notice off
  the page.
• The diagram is an SVG file. The Mermaid render hook on the site handles Markdown pages only, so the AsciiDoc
  page uses an image. The SVG uses plain SVG text, with no embedded HTML.
• Commands and names in the getting-started page match the pattern README and the AGENTS.md file in the pattern
  repository.

Checks

• hugo, run in the container image that make build uses, builds the site with these files and exits 0. The two
  pages report no warning other than the site-wide notice that the optional rouge gem is missing.
• Every AsciiDoc attribute in both pages resolves. The overview page shows the warning block and the diagram.

[openshift-ci]

Hi @BwL1289. Thanks for your PR.

I'm waiting for a validatedpatterns member to verify that this patch is reasonable to test. If it is, they should reply with /ok-to-test on its own line. Until that is done, I will not automatically test new commits in this PR, but the usual testing commands by org members will still work.

Regular contributors should join the org to skip this step.

Once the patch is verified, the new status will be reflected by the ok-to-test label.

I understand the commands that are listed here.

Details

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository.