Updating model name rewrite to be done by header key (#1331)

Author: kfswain

apix/v1alpha2/inferenceobjective_types.go

@@ -75,15 +75,6 @@ type InferenceObjectiveSpec struct {
 	// +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
-	// +kubebuilder:validation:XValidation:message="Weights should be set for all models, or none of the models.",rule="self.all(model, has(model.weight)) || self.all(model, !has(model.weight))"
-	TargetModels []TargetModel `json:"targetModels,omitempty"`
-
 	// PoolRef is a reference to the inference pool, the pool must exist in the same namespace.
 	//
 	// +kubebuilder:validation:Required
@@ -131,39 +122,6 @@ const (
 	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 InferenceObjective 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 a weight is set for any targetModel, it must be set for all targetModels.
-	// Conversely weights are optional, so long as ALL targetModels do not specify a weight.
-	//
-	// +optional
-	// +kubebuilder:validation:Minimum=1
-	// +kubebuilder:validation:Maximum=1000000
-	Weight *int32 `json:"weight,omitempty"`
-}
-
 // InferenceObjectiveStatus defines the observed state of InferenceObjective
 type InferenceObjectiveStatus struct {
 	// Conditions track the state of the InferenceObjective.

apix/v1alpha2/zz_generated.deepcopy.go

@@ -108,52 +108,6 @@ spec:
                 required:
                 - name
                 type: object
-              targetModels:
-                description: |-
-                  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.
-                items:
-                  description: |-
-                    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 InferenceObjective object.
-                  properties:
-                    name:
-                      description: Name is the name of the adapter or base model,
-                        as expected by the ModelServer.
-                      maxLength: 253
-                      type: string
-                    weight:
-                      description: |-
-                        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 a weight is set for any targetModel, it must be set for all targetModels.
-                        Conversely weights are optional, so long as ALL targetModels do not specify a weight.
-                      format: int32
-                      maximum: 1000000
-                      minimum: 1
-                      type: integer
-                  required:
-                  - name
-                  type: object
-                maxItems: 10
-                type: array
-                x-kubernetes-validations:
-                - message: Weights should be set for all models, or none of the models.
-                  rule: self.all(model, has(model.weight)) || self.all(model, !has(model.weight))
             required:
             - poolRef
             type: object

client-go/applyconfiguration/apix/v1alpha2/inferenceobjectivespec.go

@@ -6,9 +6,6 @@ spec:
   criticality: Standard
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: food-review-1
-    weight: 100
 ---
 apiVersion: inference.networking.x-k8s.io/v1alpha2
 kind: InferenceObjective

client-go/applyconfiguration/apix/v1alpha2/targetmodel.go

@@ -6,9 +6,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-0
-    weight: 100
 
 ---
 
@@ -20,9 +17,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-1
-    weight: 100
 
 ---
 
@@ -34,9 +28,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-2
-    weight: 100
 
 ---
 
@@ -48,9 +39,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-3
-    weight: 100
 
 ---
 
@@ -62,9 +50,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-4
-    weight: 100
 
 ---
 
@@ -76,9 +61,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-5
-    weight: 100
 
 ---
 
@@ -90,9 +72,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-6
-    weight: 100
 
 ---
 
@@ -104,9 +83,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-7
-    weight: 100
 
 ---
 
@@ -118,9 +94,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-8
-    weight: 100
 
 ---
 
@@ -132,9 +105,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-9
-    weight: 100
 
 ---
 
@@ -146,9 +116,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-10
-    weight: 100
 
 ---
 
@@ -160,9 +127,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-11
-    weight: 100
 
 ---
 
@@ -174,9 +138,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-12
-    weight: 100
 
 
 ---
@@ -189,9 +150,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-13
-    weight: 100
 
 
 ---
@@ -204,9 +162,6 @@ spec:
   criticality: Critical
   poolRef:
     name: vllm-llama3-8b-instruct
-  targetModels:
-  - name: adapter-14
-    weight: 100
 
 ---