Recipe
vllm
vLLM as a self-hosted inference server for local development via Docker Compose. Synthesized-mode Workload: the image, the command line, the environment, the model-cache volume and the weights-pull step are translated from the Workload kind by the compose provider. The weights pull is an init container, so it becomes a run-to-completion service that the serving service waits on before it starts. The model value is a deterministic pointer that step resolves at start; the compiler never fetches weights. Both services mount the same named model-cache volume, so the weights outlive the containers and a restart re-runs the pull step against an already-populated cache — how the downloader reconciles that is the downloader's own behaviour. When the optional model_pull_token credential slot is attached its value arrives on the inject pipe and is rendered as the HF_TOKEN environment variable on the weights-pull service, which is therefore also the key the attached credential must publish under; unattached, no such variable is emitted and weights are pulled anonymously. An attached api_key is rendered the same way as VLLM_API_KEY on the serving service, and the server then requires it of every caller under /v1. A GPU count is reserved as that many NVIDIA GPUs for the serving service, which the Docker host must provide. Compose is single-host, so the replica count and the GPU runtime class the Kubernetes realization honours are not honoured here; the build reports each as an unsupported-field warning naming the setting rather than dropping it in silence. provides.host is the compose service name, which a consumer on the same compose network resolves directly.
Herkunft
- Inhalts-Digest
- sha256:c28c526c53c3493724e66dd87738ab3f4d13555f15acd0c558dd9a2f70d5ecbc
- Veröffentlicht
- 2026-11-10T10:21:30Z
- Signaturidentität
- https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
Signatur
- Offiziellapplication/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:e91af8a7f9d69936f300bfb1f65c533703b680658ffbbe37ba386ecbccd012bf
Referenz zu dieser Version
oci://hub.aggrega.ai/recipe/compose/vllm:1.0.0- Ziel
- —
- Implementiert
- core/ai-model/vllm:1.0.0
Stellt bereit
Deterministische Zeigervorlagen, die dieses Rezept für Konsumenten verdrahtet.
| Name | Vorlage |
|---|---|
| host | {{ .context.instance_id }} |
| port | {{ .infra.port }} |
| endpoint | http://{{ .context.instance_id }}:{{ .infra.port }}/v1 |
| model | {{ default .values.model .values.served_model_name }} |
| protocol | http |
| metrics_endpoint | http://{{ .context.instance_id }}:{{ .infra.port }}/metrics |
| metrics_service | |
| metrics_service_port | |
| metrics_pod_selector | |
| metrics_pod_port | |
| metrics_path |
Workload
Workload · form: stateless · replicas: {{ · containers: main
Lokale Variablen
Keine lokalen Variablen deklariert.
Wertezuordnung
Keine Wertezuordnung deklariert.
Beziehungen
Typisierte Kanten zu und von anderen veröffentlichten Entitäten. Eine Referenz ohne veröffentlichtes Ziel wird als unterbrochene Kante statt als Link dargestellt.
Verwendet
- implementiertimplementiertVertrag kompatibel
core/ai-model/vllm:1.0.0
Alle erforderlichen Ausgaben sind erfüllt, und jede bereitgestellte Ausgabe ist im Vertrag genannt.
Verwendet von
Nichts im Katalog hängt von dieser Entität ab.