Recipe
docker-model-runner
Docker Model Runner as a self-hosted inference server on Kubernetes, synthesized as a StatefulSet running the runner's own image. It serves the OCI model reference the Aggregate names, the same reference the Docker Compose realization hands the host's runner, so one Aggregate asks both targets for the same model. A pull step running the same image puts the model into a per-replica model cache before the server starts. The server applies the context size and runtime flags each time it starts, and serves the OpenAI-compatible API under /engines/v1 behind a ClusterIP Service. The compiler never fetches the model. This realization is synthesized because the project's own Helm chart fails the maintained and complete tests: it lags the runner's releases, and it exposes no setting for the context size, runtime flags, compute resources or listen port. It is also published to no chart repository. provides.host is the bare in-cluster name of the Service, with no namespace, so a consumer in another namespace qualifies it itself. infra.endpoint, the host runner's address on Docker Compose, is refused here.
Procedencia
- Digest del contenido
- sha256:9f5fe4734eef47c6afe621aaf1b546c1aad7467ba403f8a1e856284457867cbd
- Publicado
- 2026-11-10T10:23:16Z
- 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
sha256:1cb0a71537ad3d5999068177f4b7e55d20c62a76eef82d0c38e43487f1efc05d
Referencia en esta versión
oci://hub.aggrega.ai/recipe/helm/docker-model-runner:1.0.0- Destino
- —
- Implementa
- core/ai-model/docker-model-runner:1.0.0
Proporciona
Plantillas de punteros deterministas que esta receta cablea para los consumidores.
| Nombre | Plantilla |
|---|---|
| host | {{ .context.rendered_name }}-default |
| port | {{ .locals.port }} |
| endpoint | http://{{ .context.rendered_name }}-default:{{ .locals.port }}/engines/v1 |
| model | {{ .values.model }} |
| protocol | http |
Workload
Workload · form: stateful · replicas: {{ · containers: main
Variables locales
| Nombre | Plantilla |
|---|---|
| port | {{ optional .infra "port" 12434 }} |
| gpu_count | {{ optional (optional .infra "gpu" dict) "count" 0 }} |
| runtime_class | {{ optional (optional .infra "gpu" dict) "runtime_class" "" }} |
| image | docker/model-runner:{{ optional .infra "engine_version" "v1.2.8" }}{{ if ne .locals.gpu_count "0" }}-cuda{{ end }} |
| replicas | {{ optional .infra "replicas" 1 }} |
| cpu | {{ optional (optional .infra "compute" dict) "cpu" "1" }} |
| memory | {{ optional (optional .infra "compute" dict) "memory" "4Gi" }} |
| cache_size | {{ optional (optional .infra "model_cache" dict) "size" "20Gi" }} |
| cache_class | {{ optional (optional .infra "model_cache" dict) "class" "" }} |
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/docker-model-runner: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.