Esta página se tradujo automáticamente. Leer el original en inglés.

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

OficialFirmado por una identidad de firma que este catálogo reconoce como editor oficial.
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.

NombrePlantilla
host{{ .context.instance_id }}-predictor
port80
endpointhttp://{{ .context.instance_id }}-predictor/v1
model{{ default .values.model .values.served_model_name }}
protocolhttp
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.

Referencia del concepto Recipe →

El catálogo de Aggrega — un índice abierto de componentes, funcionalidades, recetas y los plugins que los renderizan.

Creado con el sistema de diseño compartido de Aggrega.

Privacidad