Recipe
vllm
vLLM as a self-hosted inference server on Kubernetes via the helm provider's Workload synthesis, running the official upstream image directly (no external Helm chart). Renders a StatefulSet: a weights-pull initContainer resolves the model pointer into a per-replica model-cache volume, and the serving container mounts the same volume and serves the OpenAI-compatible API behind a ClusterIP Service. The model value is a deterministic pointer the initContainer resolves at pod start; the compiler never fetches weights. When the optional model_pull_token credential slot is attached the token reaches the initContainer as an env secretKeyRef, so it never appears in the rendered manifest; unattached, weights are pulled anonymously, byte-identically to a recipe with no slot. When the optional api_key slot is attached the key reaches the serving container as VLLM_API_KEY the same way, and the server requires it of every caller under /v1; unattached, it requires none. provides.host is the bare, self-contained in-cluster service name; a consumer in another namespace qualifies it on its own side. provides.metrics_endpoint names the server's metrics on the same Service while it runs one replica; above one it is empty and metrics_service names that Service for a scraper to discover every replica behind it.
Provenienza
- Digest del contenuto
- sha256:b7e2a07da70253727e8cce5267d1000fb9f03ee57bea809b17922fae4b5bf62c
- Pubblicato
- 2026-11-10T10:28:02Z
- Identità di firma
- https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
Firma
- Ufficialeapplication/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:aac522f6ab46c06eba722df4dd23c4c23e1d2d7b257c557dd91e852f8cd02822
Riferimento a questa versione
oci://hub.aggrega.ai/recipe/helm/vllm:1.0.0- Destinazione
- —
- Implementa
- core/ai-model/vllm:1.0.0
Fornisce
Modelli di puntatori deterministici che questa ricetta collega per i consumatori.
| Nome | Modello |
|---|---|
| host | {{ .context.rendered_name }}-default |
| port | {{ .infra.port }} |
| endpoint | http://{{ .context.rendered_name }}-default:{{ .infra.port }}/v1 |
| model | {{ default .values.model .values.served_model_name }} |
| protocol | http |
| metrics_endpoint | {{ if le (int .infra.replicas) 1 }}http://{{ .context.rendered_name }}-default:{{ .infra.port }}/metrics{{ end }} |
| metrics_service | {{ if gt (int .infra.replicas) 1 }}{{ .context.rendered_name }}-default{{ end }} |
| metrics_service_port | {{ if gt (int .infra.replicas) 1 }}http{{ end }} |
| metrics_pod_selector | |
| metrics_pod_port | |
| metrics_path | {{ if gt (int .infra.replicas) 1 }}/metrics{{ end }} |
Workload
Workload · form: stateful · replicas: {{ · containers: main
Variabili locali
Nessuna variabile locale dichiarata.
Mappatura dei valori
Nessuna mappatura dei valori dichiarata.
Relazioni
Archi tipizzati da e verso altre entità pubblicate. Un riferimento senza una destinazione pubblicata viene mostrato come arco interrotto anziché come link.
Usa
- implementaimplementacontratto compatibile
core/ai-model/vllm:1.0.0
Tutti gli output obbligatori sono soddisfatti e ogni output fornito è nominato nel contratto.
Usato da
Nulla nel catalogo dipende da questa entità.