fix api scheme (#674)

* fix api scheme Signed-off-by: kerthcet <kerthcet@gmail.com> * Address comments Signed-off-by: kerthcet <kerthcet@gmail.com> * Fix pointer might be nil error Signed-off-by: kerthcet <kerthcet@gmail.com> --------- Signed-off-by: kerthcet <kerthcet@gmail.com>
vllm-project · Feb 17, 2025 · bc17678 · bc17678
1 parent 70bbce6
commit bc17678
Show file tree

Hide file tree

Showing 10 changed files with 35 additions and 19 deletions.
diff --git a/Makefile b/Makefile
@@ -59,7 +59,7 @@ manifests: controller-gen ## Generate WebhookConfiguration, ClusterRole and Cust
 .PHONY: generate
 generate: controller-gen ## Generate code containing DeepCopy, DeepCopyInto, and DeepCopyObject method implementations.
 	$(CONTROLLER_GEN) object:headerFile="hack/boilerplate.go.txt" paths="./..."
-	
+
 .PHONY: update-codegen
 update-codegen:
 	sh ./hack/update-codegen.sh
@@ -137,7 +137,7 @@ define push_image
 endef
 
 .PHONY: docker-build-all
-docker-build-all: 
+docker-build-all:
 	make -j $(nproc) docker-build-controller-manager docker-build-gateway-plugins docker-build-runtime docker-build-metadata-service ## Build all docker images
 
 .PHONY: docker-build-controller-manager
@@ -157,7 +157,7 @@ docker-build-metadata-service: ## Build docker image with the metadata-service.
 	$(call build_and_tag,metadata-service,Dockerfile.metadata)
 
 .PHONY: docker-push-all
-docker-push-all: 
+docker-push-all:
 	make -j $(nproc) docker-push-controller-manager docker-push-gateway-plugins docker-push-runtime docker-push-metadata-service ## Push all docker images
 
 .PHONY: docker-push-controller-manager
@@ -212,9 +212,9 @@ endif
 .PHONY: install
 install: manifests kustomize ## Install CRDs into the K8s cluster specified in ~/.kube/config.
 	$(KUSTOMIZE) build config/crd | $(KUBECTL) apply -f -
-    ## helm creates objects without aibrix prefix, hence deploying gateway components outside of kustomization	
+    ## helm creates objects without aibrix prefix, hence deploying gateway components outside of kustomization
 	$(KUBECTL) create -k config/dependency
-	
+
 .PHONY: uninstall
 uninstall: manifests kustomize ## Uninstall CRDs from the K8s cluster specified in ~/.kube/config. Call with ignore-not-found=true to ignore resource not found errors during deletion.
 	$(KUBECTL) delete --ignore-not-found=$(ignore-not-found) -k config/dependency
@@ -231,9 +231,9 @@ undeploy: kustomize ## Undeploy controller from the K8s cluster specified in ~/.
 .PHONY: install-vke
 install-vke: manifests kustomize ## Install CRDs into the K8s cluster specified in ~/.kube/config.
 	$(KUSTOMIZE) build config/crd | $(KUBECTL) apply -f -
-    ## helm creates objects without aibrix prefix, hence deploying gateway components outside of kustomization	
+    ## helm creates objects without aibrix prefix, hence deploying gateway components outside of kustomization
 	$(KUBECTL) create -k config/overlays/vke/dependency
-	
+
 .PHONY: uninstall-vke
 uninstall-vke: manifests kustomize ## Uninstall CRDs from the K8s cluster specified in ~/.kube/config. Call with ignore-not-found=true to ignore resource not found errors during deletion.
 	$(KUBECTL) delete --ignore-not-found=$(ignore-not-found) -k config/overlays/vke/dependency

diff --git a/api/autoscaling/v1alpha1/podautoscaler_types.go b/api/autoscaling/v1alpha1/podautoscaler_types.go
@@ -23,7 +23,6 @@ import (
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 )
 
-// EDIT THIS FILE!  THIS IS SCAFFOLDING FOR YOU TO OWN!
 // NOTE: json tags are required.  Any new fields you add must have json tags for the fields to be serialized.
 // INSERT ADDITIONAL SPEC FIELDS - desired state of cluster
 // Important: Run "make" to regenerate code after modifying this file
@@ -57,16 +56,19 @@ type PodAutoscalerSpec struct {
 	//PodSelector *metav1.LabelSelector `json:"podSelector,omitempty"`
 
 	// MinReplicas is the minimum number of replicas to which the target can be scaled down.
+	// +optional
 	MinReplicas *int32 `json:"minReplicas,omitempty"`
 
 	// MaxReplicas is the maximum number of replicas to which the target can be scaled up.
 	// It cannot be less than minReplicas
 	MaxReplicas int32 `json:"maxReplicas"`
 
 	// MetricsSources defines a list of sources from which metrics are collected to make scaling decisions.
+	// +kubebuilder:validation:MinItems=1
 	MetricsSources []MetricSource `json:"metricsSources,omitempty"`
 
 	// ScalingStrategy defines the strategy to use for scaling.
+	// +kubebuilder:validation:Enum={HPA,KPA,APA}
 	ScalingStrategy ScalingStrategyType `json:"scalingStrategy"`
 }
 
@@ -103,8 +105,10 @@ const (
 // MetricSource defines an endpoint and path from which metrics are collected.
 type MetricSource struct {
 	// access an endpoint or scan a list of k8s pod
+	// +kubebuilder:validation:Enum={pod,domain}
 	MetricSourceType MetricSourceType `json:"metricSourceType"`
 	// http or https
+	// +kubebuilder:validation:Enum={http,https}
 	ProtocolType ProtocolType `json:"protocolType"`
 	// e.g. service1.example.com. meaningless for MetricSourceType.POD
 	Endpoint string `json:"endpoint,omitempty"`

diff --git a/api/model/v1alpha1/modeladapter_types.go b/api/model/v1alpha1/modeladapter_types.go
@@ -21,15 +21,14 @@ import (
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 )
 
-// EDIT THIS FILE!  THIS IS SCAFFOLDING FOR YOU TO OWN!
 // NOTE: json tags are required.  Any new fields you add must have json tags for the fields to be serialized.
 
 // ModelAdapterSpec defines the desired state of ModelAdapter
 type ModelAdapterSpec struct {
 
 	// BaseModel is the identifier for the base model to which the ModelAdapter will be attached.
 	// +optional
-	BaseModel string `json:"baseModel,omitempty"`
+	BaseModel *string `json:"baseModel,omitempty"`
 
 	// PodSelector is a label query over pods that should match the ModelAdapter configuration.
 	// +kubebuilder:validation:Required

diff --git a/api/orchestration/v1alpha1/kvcache_types.go b/api/orchestration/v1alpha1/kvcache_types.go
@@ -35,7 +35,7 @@ type ServiceConfig struct {
 
 	// NodePort specifies the port on each node on which this service is exposed when using NodePort type.
 	// +kubebuilder:validation:Optional
-	NodePort int32 `json:"nodePort,omitempty"`
+	NodePort *int32 `json:"nodePort,omitempty"`
 }
 
 // MetadataConfig holds the configuration about the kv cache metadata service

diff --git a/api/orchestration/v1alpha1/rayclusterfleet_types.go b/api/orchestration/v1alpha1/rayclusterfleet_types.go
@@ -22,13 +22,13 @@ import (
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 )
 
-// EDIT THIS FILE!  THIS IS SCAFFOLDING FOR YOU TO OWN!
 // NOTE: json tags are required.  Any new fields you add must have json tags for the fields to be serialized.
 
 // RayClusterFleetSpec defines the desired state of RayClusterFleet
 type RayClusterFleetSpec struct {
 	// Number of desired pods. This is a pointer to distinguish between explicit
 	// zero and not specified. Defaults to 1.
+	// +kubebuilder:default=1
 	// +optional
 	Replicas *int32 `json:"replicas,omitempty" protobuf:"varint,1,opt,name=replicas"`
 
@@ -55,6 +55,7 @@ type RayClusterFleetSpec struct {
 	// The number of old ReplicaSets to retain to allow rollback.
 	// This is a pointer to distinguish between explicit zero and not specified.
 	// Defaults to 10.
+	// +kubebuilder:default=10
 	// +optional
 	RevisionHistoryLimit *int32 `json:"revisionHistoryLimit,omitempty" protobuf:"varint,6,opt,name=revisionHistoryLimit"`
 
@@ -67,6 +68,8 @@ type RayClusterFleetSpec struct {
 	// process failed deployments and a condition with a ProgressDeadlineExceeded
 	// reason will be surfaced in the deployment status. Note that progress will
 	// not be estimated during the time a deployment is paused. Defaults to 600s.
+	// +kubebuilder:default=600
+	// +optional
 	ProgressDeadlineSeconds *int32 `json:"progressDeadlineSeconds,omitempty" protobuf:"varint,9,opt,name=progressDeadlineSeconds"`
 }
 

diff --git a/api/orchestration/v1alpha1/rayclusterreplicaset_types.go b/api/orchestration/v1alpha1/rayclusterreplicaset_types.go
@@ -30,6 +30,7 @@ type RayClusterReplicaSetSpec struct {
 	// This is a pointer to distinguish between explicit zero and unspecified.
 	// Defaults to 1.
 	// More info: https://kubernetes.io/docs/concepts/workloads/controllers/replicationcontroller/#what-is-a-replicationcontroller
+	// +kubebuilder:default=1
 	// +optional
 	Replicas *int32 `json:"replicas,omitempty" protobuf:"varint,1,opt,name=replicas"`
 
@@ -43,6 +44,7 @@ type RayClusterReplicaSetSpec struct {
 	// Label keys and values that must match in order to be controlled by this replica set.
 	// It must match the pod template's labels.
 	// More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/#label-selectors
+	// +optional
 	Selector *metav1.LabelSelector `json:"selector" protobuf:"bytes,2,opt,name=selector"`
 
 	// Template is the object that describes the pod that will be created if

diff --git a/api/orchestration/v1alpha1/zz_generated.deepcopy.go b/api/orchestration/v1alpha1/zz_generated.deepcopy.go
diff --git a/development/README.md b/development/README.md
@@ -4,7 +4,7 @@
 
 Here are some essential resources for anyone interested in AIBrix:
 
-- **Documentation and Tutorials**: [View Tutorials](https://github.com/aibrix/aibrix/tree/main/docs/tutorial)
+- **Documentation and Tutorials**: [View Tutorials](https://github.com/aibrix/aibrix/tree/main/development/tutorial)
 - **Issue Tracker**: [View Issues](https://github.com/aibrix/aibrix/issues)
 - **Project Roadmap**: TODO
 
@@ -43,7 +43,7 @@ Alternatively, you can use [Kind](https://kind.sigs.k8s.io/) or [Minikube](https
 
 Navigate to the cloned directory and run:
 
-```  
+```
 make build
 ```
 
@@ -53,8 +53,8 @@ Build and push your image to the location specified by `IMG`:
 make docker-build docker-push IMG=<some-registry>/aibrix:tag
 ```
 
-> **NOTE:** This image ought to be published in the personal registry you specified.  
-And it is required to have access to pull the image from the working environment.  
+> **NOTE:** This image ought to be published in the personal registry you specified.
+And it is required to have access to pull the image from the working environment.
 Make sure you have the proper permission to the registry if the above commands don’t work.
 
 Install the CRDs into the cluster:

diff --git a/pkg/controller/modeladapter/resources.go b/pkg/controller/modeladapter/resources.go
@@ -62,9 +62,11 @@ func buildModelAdapterEndpointSlice(instance *modelv1alpha1.ModelAdapter, pod *c
 
 func buildModelAdapterService(instance *modelv1alpha1.ModelAdapter) *corev1.Service {
 	labels := map[string]string{
-		"model.aibrix.ai/name":         instance.Spec.BaseModel,
 		"adapter.model.aibrix.ai/name": instance.Name,
 	}
+	if instance.Spec.BaseModel != nil {
+		labels["model.aibrix.ai/name"] = *instance.Spec.BaseModel
+	}
 
 	ports := []corev1.ServicePort{
 		{

diff --git a/pkg/controller/modeladapter/resources_test.go b/pkg/controller/modeladapter/resources_test.go
@@ -24,6 +24,7 @@ import (
 	corev1 "k8s.io/api/core/v1"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/util/intstr"
+	"k8s.io/utils/ptr"
 )
 
 func TestBuildModelAdapterEndpointSlice(t *testing.T) {
@@ -75,7 +76,7 @@ func TestBuildModelAdapterService(t *testing.T) {
 			Namespace: "default",
 		},
 		Spec: modelv1alpha1.ModelAdapterSpec{
-			BaseModel: "test-model",
+			BaseModel: ptr.To[string]("test-model"),
 		},
 	}