Find your next open-source project

Search by name, purpose, or keyword — or paste a GitHub repository URL
All skills

dynamo-recipe-runner

Select, validate, patch, and deploy an existing Dynamo Kubernetes recipe, then confirm it with a smoke request.

  • Part of NVIDIA/skills
  • 2.6k installs
  • DevOps & Self-hosting · Containers and clusters

When to use it

You already have a Dynamo recipe target (model, framework, GPU) and a cluster, but still need the right recipe picked, patched, and deployed.

For example

You say

Use dynamo-recipe-runner to deploy the Qwen vLLM disaggregated recipe on my 8xB200 cluster in namespace dynamo, then smoke test it.

You get
  • Selected recipe path
  • Patched values list
  • Smoke-test result

How it works

  • Patches only the minimal recipe values instead of rewriting whole YAML files.
  • If the cluster is unreachable, it returns exact commands rather than pretending to deploy.

Before installing

Needs Python 3.10+, a configured kubectl cluster context, a default storage class, and a Hugging Face token secret in the target namespace.

This skill includes a script your assistant may run on your computer.