v0.1 API Review

api/groupversion_info.go

@@ -0,0 +1,45 @@
+/*
+Copyright 2024 The Kubernetes Authors.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+*/
+
+// Package v1alpha1 contains API Schema definitions for the gateway v1alpha1 API group
+// +kubebuilder:object:generate=true
+// +groupName=inference.networking.x-k8s.io
+package v1alpha1
+
+import (
+	"k8s.io/apimachinery/pkg/runtime/schema"
+	"sigs.k8s.io/controller-runtime/pkg/scheme"
+)
+
+var (
+	// GroupVersion is group version used to register these objects
+	GroupVersion = schema.GroupVersion{Group: "inference.networking.x-k8s.io", Version: "v1alpha1"}
+
+	// SchemeGroupVersion is alias to GroupVersion for client-go libraries.
+	// It is required by pkg/client/informers/externalversions/...
+	SchemeGroupVersion = GroupVersion
+
+	// SchemeBuilder is used to add go types to the GroupVersionKind scheme
+	SchemeBuilder = &scheme.Builder{GroupVersion: GroupVersion}
+
+	// AddToScheme adds the types in this group-version to the given scheme.
+	AddToScheme = SchemeBuilder.AddToScheme
+)
+
+// Resource is required by pkg/client/listers/...
+func Resource(resource string) schema.GroupResource {
+	return GroupVersion.WithResource(resource).GroupResource()
+}

api/inferencemodel_types.go

@@ -0,0 +1,202 @@
+/*
+Copyright 2024 The Kubernetes Authors.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+*/
+
+package v1alpha1
+
+import (
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+)
+
+// InferenceModel is the Schema for the InferenceModels API.
+//
+// +kubebuilder:object:root=true
+// +kubebuilder:subresource:status
+// +genclient
+type InferenceModel struct {
+	metav1.TypeMeta   `json:",inline"`
+	metav1.ObjectMeta `json:"metadata,omitempty"`
+
+	Spec   InferenceModelSpec   `json:"spec,omitempty"`
+	Status InferenceModelStatus `json:"status,omitempty"`
+}
+
+// InferenceModelList contains a list of InferenceModel.
+//
+// +kubebuilder:object:root=true
+type InferenceModelList struct {
+	metav1.TypeMeta `json:",inline"`
+	metav1.ListMeta `json:"metadata,omitempty"`
+	Items           []InferenceModel `json:"items"`
+}
+
+// InferenceModelSpec represents the desired state of a specific model use case. This resource is
+// managed by the "Inference Workload Owner" persona.
+//
+// The Inference Workload Owner persona is someone that trains, verifies, and
+// leverages a large language model from a model frontend, drives the lifecycle
+// and rollout of new versions of those models, and defines the specific
+// performance and latency goals for the model. These workloads are
+// expected to operate within an InferencePool sharing compute capacity with other
+// InferenceModels, defined by the Inference Platform Admin.
+//
+// InferenceModel's modelName (not the ObjectMeta name) is unique for a given InferencePool,
+// if the name is reused, an error will be shown on the status of a
+// InferenceModel that attempted to reuse. The oldest InferenceModel, based on
+// creation timestamp, will be selected to remain valid. In the event of a race
+// condition, one will be selected at random.
+type InferenceModelSpec struct {
+	// ModelName is the name of the model as the users set in the "model" parameter in the requests.
+	// The name should be unique among the workloads that reference the same backend pool.
+	// This is the parameter that will be used to match the request with. In the future, we may
+	// allow to match on other request parameters. The other approach to support matching
+	// on other request parameters is to use a different ModelName per HTTPFilter.
+	// Names can be reserved without implementing an actual model in the pool.
+	// This can be done by specifying a target model and setting the weight to zero,
+	// an error will be returned specifying that no valid target model is found.
+	//
+	// +kubebuilder:validation:MaxLength=256
+	// +kubebuilder:validation:Required
+	ModelName string `json:"modelName"`
+
+	// Criticality defines how important it is to serve the model compared to other models referencing the same pool.
+	// The lack of defaulting is intentional, the behavior of not setting criticality future-proofs the API without complicating.
+	//
+	// +optional
+	Criticality *Criticality `json:"criticality,omitempty"`
+
+	// TargetModels allow multiple versions of a model for traffic splitting.
+	// If not specified, the target model name is defaulted to the modelName parameter.
+	// modelName is often in reference to a LoRA adapter.
+	//
+	// +optional
+	// +kubebuilder:validation:MaxItems=10
+	TargetModels []TargetModel `json:"targetModels,omitempty"`
+
+	// PoolRef is a reference to the inference pool, the pool must exist in the same namespace.
+	//
+	// +kubebuilder:validation:Required
+	PoolRef PoolObjectReference `json:"poolRef"`
+}
+
+// PoolObjectReference identifies an API object within the namespace of the
+// referrer.
+type PoolObjectReference struct {
+	// Group is the group of the referent.
+	//
+	// +optional
+	// +kubebuilder:default="inference.networking.x-k8s.io"
+	// +kubebuilder:validation:MaxLength=253
+	// +kubebuilder:validation:Pattern=`^$|^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$`
+	Group string `json:"group,omitempty"`
+
+	// Kind is kind of the referent. For example "InferencePool".
+	//
+	// +optional
+	// +kubebuilder:default="InferencePool"
+	// +kubebuilder:validation:MinLength=1
+	// +kubebuilder:validation:MaxLength=63
+	// +kubebuilder:validation:Pattern=`^[a-zA-Z]([-a-zA-Z0-9]*[a-zA-Z0-9])?$`
+	Kind string `json:"kind,omitempty"`
+
+	// Name is the name of the referent.
+	//
+	// +kubebuilder:validation:MinLength=1
+	// +kubebuilder:validation:MaxLength=253
+	// +kubebuilder:validation:Required
+	Name string `json:"name"`
+}
+
+// Criticality defines how important it is to serve the model compared to other models.
+// +kubebuilder:validation:Enum=Critical;Default;Sheddable
+type Criticality string
+
+const (
+	// Critical defines the highest level of criticality. Requests to this band will be shed last.
+	Critical Criticality = "Critical"
+
+	// Default defines the default criticality level and is more important than Sheddable but less
+	// important than Critical. Requests in this band will be shed before critical traffic.
+	Default Criticality = "Default"
+
+	// Sheddable defines the lowest level of criticality. Requests to this band will be shed before
+	// all other bands.
+	Sheddable Criticality = "Sheddable"
+)
+
+// TargetModel represents a deployed model or a LoRA adapter. The
+// Name field is expected to match the name of the LoRA adapter
+// (or base model) as it is registered within the model server. Inference
+// Gateway assumes that the model exists on the model server and it's the
+// responsibility of the user to validate a correct match. Should a model fail
+// to exist at request time, the error is processed by the Inference Gateway
+// and emitted on the appropriate InferenceModel object.
+type TargetModel struct {
+	// Name is the name of the adapter or base model, as expected by the ModelServer.
+	//
+	// +kubebuilder:validation:MaxLength=253
+	// +kubebuilder:validation:Required
+	Name string `json:"name"`
+
+	// Weight is used to determine the proportion of traffic that should be
+	// sent to this model when multiple target models are specified.
+	//
+	// Weight defines the proportion of requests forwarded to the specified
+	// model. This is computed as weight/(sum of all weights in this
+	// TargetModels list). For non-zero values, there may be some epsilon from
+	// the exact proportion defined here depending on the precision an
+	// implementation supports. Weight is not a percentage and the sum of
+	// weights does not need to equal 100.
+	//
+	// If only one model is specified and it has a weight greater than 0, 100%
+	// of the traffic is forwarded to that model. If weight is set to 0, no
+	// traffic should be forwarded for this model.
+	//
+	// +optional
+	// +kubebuilder:validation:Minimum=0
+	// +kubebuilder:validation:Maximum=1000000
+	Weight *int32 `json:"weight,omitempty"`
+}
+
+// InferenceModelStatus defines the observed state of InferenceModel
+type InferenceModelStatus struct {
+	// Conditions track the state of the InferenceModel.
+	Conditions []metav1.Condition `json:"conditions,omitempty"`
+}
+
+// InferenceModelConditionType is a type of condition for the InferenceModel.
+type InferenceModelConditionType string
+
+// InferenceModelConditionReason is the reason for a given InferenceModelConditionType.
+type InferenceModelConditionReason string
+
+const (
+	// This condition indicates whether the model is ready for traffic or not, and why.
+	ModelConditionReady InferenceModelConditionType = "Ready"
+
+	// Desired state. Model is ready for serving with no conflicts or issues.
+	ModelReasonReady InferenceModelConditionReason = "Ready"
+
+	// This reason is used when a given ModelName already exists within the pool.
+	// Details about naming conflict resolution are on the ModelName field itself.
+	ModelReasonNameInUse InferenceModelConditionReason = "ModelNameInUse"
+
+	// This reason is the initial state, and indicates that the controller has not yet reconciled the InferenceModel.
+	ModelReasonPending InferenceModelConditionReason = "Pending"
+)
+
+func init() {
+	SchemeBuilder.Register(&InferenceModel{}, &InferenceModelList{})
+}

api/inferencepool_types.go

@@ -0,0 +1,133 @@
+/*
+Copyright 2024 The Kubernetes Authors.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+*/
+
+package v1alpha1
+
+import (
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+)
+
+// InferencePool is the Schema for the InferencePools API.
+//
+// +kubebuilder:object:root=true
+// +kubebuilder:subresource:status
+// +genclient
+type InferencePool struct {
+	metav1.TypeMeta   `json:",inline"`
+	metav1.ObjectMeta `json:"metadata,omitempty"`
+
+	Spec   InferencePoolSpec   `json:"spec,omitempty"`
+	Status InferencePoolStatus `json:"status,omitempty"`
+}
+
+// InferencePoolList contains a list of InferencePool.
+//
+// +kubebuilder:object:root=true
+type InferencePoolList struct {
+	metav1.TypeMeta `json:",inline"`
+	metav1.ListMeta `json:"metadata,omitempty"`
+	Items           []InferencePool `json:"items"`
+}
+
+// InferencePoolSpec defines the desired state of InferencePool
+type InferencePoolSpec struct {
+	// Selector defines a map of label to watch model server pods
+	// that should be included in the InferencePool.
+	// 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.
+	//
+	// +kubebuilder:validation:Required
+	Selector map[LabelKey]LabelValue `json:"selector"`
+
+	// TargetPortNumber defines the port number to access the selected model servers.
+	// The number must be in the range 1 to 65535.
+	//
+	// +kubebuilder:validation:Minimum=1
+	// +kubebuilder:validation:Maximum=65535
+	// +kubebuilder:validation:Required
+	TargetPortNumber int32 `json:"targetPortNumber"`
+}
+
+// LabelKey was 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]$`
+type LabelKey string
+
+// LabelValue is the value of a label. This is used for validation
+// of maps. This matches the Kubernetes label validation rules:
+// * must be 63 characters or less (can be empty),
+// * unless empty, must begin and end with an alphanumeric character ([a-z0-9A-Z]),
+// * could contain dashes (-), underscores (_), dots (.), and alphanumerics between.
+// Labels are case sensitive, so: my-label and My-Label are considered distinct.
+//
+// Valid values include:
+//
+// * MyValue
+// * my.name
+// * 123-my-value
+//
+// +kubebuilder:validation:MinLength=0
+// +kubebuilder:validation:MaxLength=63
+// +kubebuilder:validation:Pattern=`^(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])?$`
+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"`
+}
+
+// InferencePoolConditionType is a type of condition for the InferencePool
+type InferencePoolConditionType string
+
+// InferencePoolConditionReason is the reason for a given InferencePoolConditionType
+type InferencePoolConditionReason string
+
+const (
+	// This condition indicates whether the pool is ready for traffic or not, and why.
+	PoolConditionReady InferencePoolConditionType = "Ready"
+
+	// Desired state. The pool and its components are initialized and ready for traffic.
+	PoolReasonReady InferencePoolConditionReason = "Ready"
+
+	// This reason is used when the EPP has not yet passed health checks, or has started failing them.
+	PoolReasonEPPNotHealthy InferencePoolConditionReason = "EndpointPickerNotHealthy"
+
+	// This reason is the initial state, and indicates that the controller has not yet reconciled this pool.
+	PoolReasonPending InferencePoolConditionReason = "Pending"
+)
+
+func init() {
+	SchemeBuilder.Register(&InferencePool{}, &InferencePoolList{})
+}