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.
More Containers and clusters skills
See all- kubernetes-specialist14.9kCreates and manages Kubernetes workloads, manifests, Helm charts, RBAC rules and pod debugging.
- container-layer16Builds and caches a custom container environment so installs and config survive ephemeral sessions.
- setup-gke-sandboxesDeploys, verifies or tears down gke-sandboxes in a Google Cloud project and connects a backend to it.
Also in this pack
- accelerated-computing-cudf3.2kGuides GPU DataFrame work with cuDF, including pandas acceleration, joins, groupby, file I/O and multi-GPU jobs.
- cuopt-developer2.8kModifies, builds, tests, and debugs NVIDIA cuOpt source code and prepares contributions.
- cuopt-install2.6kInstalls cuOpt for Python, C, or server via pip, conda, or Docker and verifies it works.
- data-designer2.6kGenerates a synthetic dataset from your description of the data you need.