Feedback updates

Author: kfswain

api/v1alpha1/inferencemodel_types.go

@@ -60,7 +60,6 @@ type InferenceModelSpec struct {
 	// modelName is often in reference to a LoRA adapter.
 	//
 	// +optional
-	// +kubebuilder:validation:MinItems=1
 	// +kubebuilder:validation:MaxItems=10
 	TargetModels []TargetModel `json:"targetModels,omitempty"`
 	// Reference to the inference pool, the pool must exist in the same namespace.
@@ -132,7 +131,7 @@ type TargetModel struct {
 	// +kubebuilder:default=1
 	// +kubebuilder:validation:Minimum=0
 	// +kubebuilder:validation:Maximum=1000000
-	Weight int `json:"weight,omitempty"`
+	Weight int32 `json:"weight,omitempty"`
 }
 
 // InferenceModelStatus defines the observed state of InferenceModel

api/v1alpha1/inferencepool_types.go

@@ -33,7 +33,7 @@ type InferencePoolSpec struct {
 	// map used for Service selectors instead of the full Kubernetes LabelSelector type.
 	//
 	// +kubebuilder:validation:Required
-	Selector map[LabelString]LabelString `json:"selector,omitempty"`
+	Selector map[LabelKey]LabelValue `json:"selector,omitempty"`
 
 	// TargetPort is the port number that the model servers within the pool expect
 	// to recieve traffic from.
@@ -42,22 +42,56 @@ type InferencePoolSpec struct {
 	// +kubebuilder:validation:Minimum=0
 	// +kubebuilder:validation:Maximum=65535
 	// +kubebuilder:validation:Required
-	TargetPort int32 `json:"targetPort,omitempty"`
+	TargetPortNumber int32 `json:"targetPortNumber,omitempty"`
 }
 
+// Originally copied from: https://github.com/kubernetes-sigs/gateway-api/blob/99a3934c6bc1ce0874f3a4c5f20cafd8977ffcb4/apis/v1/shared_types.go#L694-L731
+// Duplicated as to not take an unexpected dependency on gw's API.
+//
+// LabelKey is the key of a label. This is used for validation
+// of maps. This matches the Kubernetes "qualified name" validation that is used for labels.
+//
+// Valid values include:
+//
+// * example
+// * example.com
+// * example.com/path
+// * example.com/path.html
+//
+// Invalid values include:
+//
+// * example~ - "~" is an invalid character
+// * example.com. - can not start or end with "."
+//
+// +kubebuilder:validation:MinLength=1
+// +kubebuilder:validation:MaxLength=253
+// +kubebuilder:validation:Pattern=`^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?([A-Za-z0-9][-A-Za-z0-9_.]{0,61})?[A-Za-z0-9]$`
+type LabelKey string
+
+// LabelValue is the value of a label. This is used for validation
+// of maps. This matches the Kubernetes label validation rules:
+// * must be 63 characters or less (can be empty),
+// * unless empty, must begin and end with an alphanumeric character ([a-z0-9A-Z]),
+// * could contain dashes (-), underscores (_), dots (.), and alphanumerics between.
+//
+// Valid values include:
+//
+// * MyValue
+// * my.name
+// * 123-my-value
+//
+// +kubebuilder:validation:MinLength=0
+// +kubebuilder:validation:MaxLength=63
+// +kubebuilder:validation:Pattern=`^(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])?$`
+type LabelValue string
+
 // InferencePoolStatus defines the observed state of InferencePool
 type InferencePoolStatus struct {
 
 	// Conditions track the state of the InferencePool.
 	Conditions []metav1.Condition `json:"conditions,omitempty"`
 }
 
-// This indirection allows us to validate this type, since there is not native map validation support
-//
-// +kubebuilder:validation:MinLength=1
-// +kubebuilder:validation:MaxLength=63
-type LabelString string
-
 // +kubebuilder:object:root=true
 // +kubebuilder:subresource:status
 // +genclient

api/v1alpha1/zz_generated.deepcopy.go

@@ -76,7 +76,8 @@ spec:
                 maxLength: 253
                 type: string
               poolRef:
-                description: Reference to the poolIt must exist in the same namespace.
+                description: Reference to the inference pool, the pool must exist
+                  in the same namespace.
                 properties:
                   group:
                     default: inference.networking.x-k8s.io
@@ -96,6 +97,8 @@ spec:
                     maxLength: 253
                     minLength: 1
                     type: string
+                required:
+                - name
                 type: object
               targetModels:
                 description: |-
@@ -121,12 +124,12 @@ spec:
                       description: |-
                         Weight is used to determine the proportion of traffic that should be
                         sent to this target model when multiple versions of the model are specified.
+                      format: int32
                       maximum: 1000000
                       minimum: 0
                       type: integer
                   type: object
                 maxItems: 10
-                minItems: 1
                 type: array
             required:
             - poolRef

client-go/applyconfiguration/api/v1alpha1/inferencemodelspec.go

@@ -41,10 +41,21 @@ spec:
             properties:
               selector:
                 additionalProperties:
-                  description: This indirection allows us to validate this type, since
-                    there is not native map validation support
+                  description: |-
+                    LabelValue is the value of a label. This is used for validation
+                    of maps. This matches the Kubernetes label validation rules:
+                    * must be 63 characters or less (can be empty),
+                    * unless empty, must begin and end with an alphanumeric character ([a-z0-9A-Z]),
+                    * could contain dashes (-), underscores (_), dots (.), and alphanumerics between.
+
+                    Valid values include:
+
+                    * MyValue
+                    * my.name
+                    * 123-my-value
                   maxLength: 63
-                  minLength: 1
+                  minLength: 0
+                  pattern: ^(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])?$
                   type: string
                 description: |-
                   Selector uses a map of label to watch model server pods
@@ -54,7 +65,7 @@ spec:
                   In some cases, implementations may translate this to a Service selector, so this matches the simple
                   map used for Service selectors instead of the full Kubernetes LabelSelector type.
                 type: object
-              targetPort:
+              targetPortNumber:
                 description: |-
                   TargetPort is the port number that the model servers within the pool expect
                   to recieve traffic from.
@@ -65,7 +76,7 @@ spec:
                 type: integer
             required:
             - selector
-            - targetPort
+            - targetPortNumber
             type: object
           status:
             description: InferencePoolStatus defines the observed state of InferencePool