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.
Provenance
- Content digest
- sha256:9f5fe4734eef47c6afe621aaf1b546c1aad7467ba403f8a1e856284457867cbd
- Published
- 2026-11-10T10:23:16Z
- Signing identity
- https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
Signature
- Officialapplication/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
Reference at this version
oci://hub.aggrega.ai/recipe/helm/docker-model-runner:1.0.0- Target
- —
- Implements
- core/ai-model/docker-model-runner:1.0.0
Provides
Deterministic pointer templates this recipe wires for consumers.
| Name | Template |
|---|---|
| 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
Locals
| Name | Template |
|---|---|
| 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" "" }} |
Values mapping
No values mapping declared.
Relationships
Typed edges to and from other published entities. A reference with no published target renders as a broken edge rather than a link.
Uses
- implementsimplementscontract compatible
core/ai-model/docker-model-runner:1.0.0
All required outputs are satisfied and every provided output is named in the contract.
Used by
Nothing in the catalog depends on this entity.