Recipe
vllm-kserve
vLLM realized as a KServe InferenceService the KServe controller reconciles, rather than a directly synthesized StatefulSet — the controller-driven realization of the same model component, selectable in the Manifest alongside the synthesis recipe. The recipe emits an InferenceService custom resource whose predictor resolves the model pointer as a storage URI; the controller turns it into a running serving workload and its predictor Service. The model value is a deterministic pointer the controller resolves at reconcile time; the compiler never fetches weights. GPU is requested directly on the predictor as the extended resource nvidia.com/gpu, with an optional runtime class. provides is filled from the predictor Service the controller creates, so a consumer wires to it exactly as it would to the synthesized realization. An attached api_key reaches the predictor as VLLM_API_KEY, taken from the credential's secret by name, so the key never appears in the custom resource. The KServe control plane is a runtime prerequisite: the build halts unless the operator affirms it is installed (infra.control_plane_present), so no custom resource is emitted into a cluster that cannot reconcile it. The InferenceService is written into the namespace the Release, or else the Aggregate, names for this component through the aggrega.ai/namespace annotation, where one is set. Every metrics key is published empty: the port and path of the metrics belong to the serving runtime the cluster registered, which the catalog does not know.
Procedencia
- Digest del contenido
- sha256:4614aae2e413c2ce4f5fa5ae9da4867bf75e2848f0131f9231b6073f6bd8704e
- Publicado
- 2026-11-10T10:27:57Z
- Identidad de firma
- https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
Firma
- Oficialapplication/vnd.dev.sigstore.bundle.v0.3+json
https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
sha256:a379bf3be43ccc8543136b5da2fd6ecc2d3f88eb85e69bdededb983ef056a8aa
Referencia en esta versión
oci://hub.aggrega.ai/recipe/helm/vllm-kserve:1.0.0- Destino
- —
- Implementa
- core/ai-model/vllm:1.0.0
Proporciona
Plantillas de punteros deterministas que esta receta cablea para los consumidores.
| Nombre | Plantilla |
|---|---|
| host | {{ .context.instance_id }}-predictor |
| port | 80 |
| endpoint | http://{{ .context.instance_id }}-predictor/v1 |
| model | {{ default .values.model .values.served_model_name }} |
| protocol | http |
| metrics_endpoint | |
| metrics_service | |
| metrics_service_port | |
| metrics_pod_selector | |
| metrics_pod_port | |
| metrics_path |
Workload
No se declaró ninguna plantilla de carga de trabajo.
Variables locales
No se declararon variables locales.
Mapeo de valores
No se declaró ningún mapeo de valores.
Relaciones
Aristas tipadas hacia y desde otras entidades publicadas. Una referencia sin un destino publicado se muestra como una arista rota en lugar de como un enlace.
Usa
- implementaimplementacontrato compatible
core/ai-model/vllm:1.0.0
Todas las salidas obligatorias se satisfacen y cada salida proporcionada está nombrada en el contrato.
Usado por
Nada en el catálogo depende de esta entidad.