Page History

// InferenceModelSpec defines the desired state of an InferenceModel.
// Two ways of deployment are provided. The first is through a docker image.
// The second is through a data store, with a manifest of model files.
// If image is provided, manifest and targetVersion will be ignored.
type InferenceModelSpec struct {
	ModelName     string               `json:"modelName"`
	DeployToLayer string               `json:"deployToLayer"`
	FrameworkType string               `json:"fraemworkType,omitemptyframeworkType"`

	// +optional
	NodeSelector  map[string]string    `json:"nodeSelector,omitempty"`

	Image         string               // +optional
	NodeName string `json:"nodeName,omitempty"`

	// +optional
	Image string `json:"image,omitempty"`

	// +optional
	Manifest      []InferenceModelFile `json:"manifest,omitempty"`

	// +optional
	TargetVersion string               `json:"targetVersion,omitempty"`

	Replicas      *int32               // +optional
	// +kubebuilder:validation:Minimum=0
	ServingPort int32 `json:"servingPort"`

	// +optional
	// +kubebuilder:validation:Minimum=0
	Replicas *int32 `json:"replicas,omitempty"`
}

// InferenceModelFile defines an archive file for a single version of the model
type InferenceModelFile struct {
	Version     string `json:"version,omitempty"`
	DownloadURL string `json:"downloadURL,omitempty"`
	Sha256sum   string `json:"sha256sum,omitempty"`
}

// InferenceModelStatus defines the observed state of InferenceModel
type InferenceModelStatus struct {
	URL            string `json:"url,omitempty"`
	ServingVersion string `json:"servingVersion,omitempty"`
}