model

Model is the Schema for the models API. A Model declares a model to be served via an inference server (llama-server, vLLM, TGI, or custom) and exposed as an OpenAI-compatible endpoint.

Schema URL

https://raw.githubusercontent.com/nlamirault/schema-hub/main/schemas/sympozium.ai/model_v1alpha1.json

▶ Usage examples

VS Code / yaml-language-server

# yaml-language-server: $schema=https://raw.githubusercontent.com/nlamirault/schema-hub/main/schemas/sympozium.ai/model_v1alpha1.json

kubeconform

kubeconform -schema-location 'https://raw.githubusercontent.com/nlamirault/schema-hub/main/schemas/{{ .Group }}/{{ .ResourceKind }}_{{ .ResourceAPIVersion }}.json' manifest.yaml

Resource Structure

apiVersionstring

APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources

kindstring

Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds

metadataobject

specobject

ModelCRDSpec defines the desired state of a Model. A Model declares a model to be served via an inference server (llama-server, vLLM, TGI, or custom) and exposed as an OpenAI-compatible endpoint.

statusobject

ModelStatus defines the observed state of a Model.