Merge master and for time being remove Kubvernor from the guides

Author: dawid-nowak

.github/ISSUE_TEMPLATE/new-release.md

@@ -41,7 +41,7 @@ This document defines the process for releasing Gateway API Inference Extension.
    tag has been published, set the appropriate environment variable or update the script. For example:
 
    ```shell
-   export VLLM_GPU=0.9.2
+   export VLLM_GPU=0.8.5
    export VLLM_CPU=0.9.3
    export VLLM_SIM=0.3.0
    ```

.github/workflows/kal.yml

@@ -20,9 +20,5 @@ jobs:
           persist-credentials: false
       - name: Set up Go
         uses: actions/setup-go@d35c59abb061a4a6fb18e82ac0862c26744d6ab5 # tag=v5.5.0
-      - name: Install Golang CI Lint
-        run: go install github.com/golangci/golangci-lint/v2/cmd/[email protected]
-      - name: Build KAL
-        run: golangci-lint custom
-      - name: run api linter
-        run: ./bin/golangci-kube-api-linter run -c ./.golangci-kal.yml ./...
+      - name: Run API Linter
+        run: make api-lint

.github/workflows/non-main-gatekeeper.yml

@@ -0,0 +1,18 @@
+name: Label non-main PRs
+
+on:
+  pull_request:
+    types: [opened, edited, synchronize, reopened]
+
+jobs:
+  add-label:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Add labels when base branch is not main
+        if: github.event.pull_request.base.ref != 'main'
+        uses: actions-ecosystem/action-add-labels@v1
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          labels: |
+            do-not-merge/hold
+            do-not-merge/cherry-pick-not-approved

Makefile

@@ -138,7 +138,9 @@ test: generate fmt vet envtest image-build verify-crds ## Run tests.
 
 .PHONY: test-unit
 test-unit: ## Run unit tests.
-	CGO_ENABLED=1 KUBEBUILDER_ASSETS="$(shell $(ENVTEST) use $(ENVTEST_K8S_VERSION) --bin-dir $(LOCALBIN) -p path)" go test ./pkg/... -race -coverprofile cover.out
+	CGO_ENABLED=1 KUBEBUILDER_ASSETS="$(shell $(ENVTEST) use $(ENVTEST_K8S_VERSION) --bin-dir $(LOCALBIN) -p path)" go test ./pkg/... -race -coverprofile cover.out; \
+	go tool cover -func=cover.out; \
+	rm cover.out
 
 .PHONY: test-integration
 test-integration: envtest ## Run integration tests.
@@ -160,8 +162,12 @@ lint-fix: golangci-lint ## Run golangci-lint linter and perform fixes
 ci-lint: golangci-lint
 	$(GOLANGCI_LINT) run --timeout 15m0s
 
+.PHONY: api-lint
+api-lint: golangci-api-lint
+	$(GOLANGCI_API_LINT) run -c .golangci-kal.yml --timeout 15m0s ./...
+
 .PHONY: verify
-verify: vet fmt-verify generate ci-lint verify-all
+verify: vet fmt-verify generate ci-lint api-lint verify-all
 	git --no-pager diff --exit-code config api client-go
 
 .PHONY: verify-crds
@@ -366,6 +372,7 @@ CONTROLLER_GEN ?= $(LOCALBIN)/controller-gen
 ENVTEST ?= $(LOCALBIN)/setup-envtest
 CRD_REF_DOCS ?= $(LOCALBIN)/crd-ref-docs
 GOLANGCI_LINT = $(LOCALBIN)/golangci-lint
+GOLANGCI_API_LINT = $(LOCALBIN)/golangci-kube-api-linter
 HELM = $(PROJECT_DIR)/bin/helm
 YQ = $(PROJECT_DIR)/bin/yq
 KUBECTL_VALIDATE = $(PROJECT_DIR)/bin/kubectl-validate
@@ -407,6 +414,11 @@ golangci-lint: $(GOLANGCI_LINT) ## Download golangci-lint locally if necessary.
 $(GOLANGCI_LINT): $(LOCALBIN)
 	$(call go-install-tool,$(GOLANGCI_LINT),github.com/golangci/golangci-lint/v2/cmd/golangci-lint,$(GOLANGCI_LINT_VERSION))
 
+.PHONY: golangci-api-lint
+golangci-api-lint: golangci-lint $(GOLANGCI_API_LINT) ## Download golangci-lint locally if necessary before building KAL
+$(GOLANGCI_API_LINT):
+	$(GOLANGCI_LINT) custom
+
 .PHONY: yq
 yq: ## Download yq locally if necessary.
 	GOBIN=$(PROJECT_DIR)/bin GO111MODULE=on go install github.com/mikefarah/yq/v4@$(YQ_VERSION)

OWNERS_ALIASES

@@ -9,6 +9,6 @@ aliases:
   - kfswain
 
   gateway-api-inference-extension-reviewers:
+  - elevran
   - liu-cong
   - robscott
-  - shaneutt

README.md

@@ -29,7 +29,8 @@ The following specific terms to this project:
   performance, availability and capabilities to optimize routing. Includes
   things like [Prefix Cache] status or [LoRA Adapters] availability.
 - **Endpoint Picker(EPP)**: An implementation of an `Inference Scheduler` with additional Routing, Flow, and Request Control layers to allow for sophisticated routing strategies. Additional info on the architecture of the EPP [here](https://github.com/kubernetes-sigs/gateway-api-inference-extension/tree/main/docs/proposals/0683-epp-architecture-proposal).
-  
+- **Body Based Router(BBR)**: An optional additional [ext-proc](https://www.envoyproxy.io/docs/envoy/latest/configuration/http/http_filters/ext_proc_filter) server that parses the http body of the inference prompt message and extracts information (currently the model name for OpenAI API style messages) into a format which can then be used by the gateway for routing purposes. Additional info [here](https://github.com/kubernetes-sigs/gateway-api-inference-extension/tree/main/pkg/bbr/README.md) and in the documentation [user guides](https://gateway-api-inference-extension.sigs.k8s.io/guides/). 
+ 
 
 The following are key industry terms that are important to understand for
 this project:

api/v1/inferencepool_types.go

@@ -96,6 +96,7 @@ type Port struct {
 
 // EndpointPickerRef specifies a reference to an Endpoint Picker extension and its
 // associated configuration.
+// +kubebuilder:validation:XValidation:rule="self.kind != 'Service' || has(self.port)",message="port is required when kind is 'Service' or unspecified (defaults to 'Service')"
 type EndpointPickerRef struct {
 	// Group is the group of the referent API object. When unspecified, the default value
 	// is "", representing the Core API group.
@@ -118,29 +119,29 @@ type EndpointPickerRef struct {
 	//
 	// +optional
 	// +kubebuilder:default=Service
-	//nolint:kubeapilinter // ignore kubeapilinter here as we want to use pointer for optional struct.
-	Kind *Kind `json:"kind,omitempty"`
+	Kind Kind `json:"kind,omitempty"`
 
 	// Name is the name of the referent API object.
 	//
 	// +required
 	Name ObjectName `json:"name,omitempty"`
 
-	// PortNumber is the port number of the Endpoint Picker extension service. When unspecified,
-	// implementations SHOULD infer a default value of 9002 when the kind field is "Service" or
-	// unspecified (defaults to "Service").
+	// Port is the port of the Endpoint Picker extension service.
+	//
+	// Port is required when the referent is a Kubernetes Service. In this
+	// case, the port number is the service port number, not the target port.
+	// For other resources, destination port might be derived from the referent
+	// resource or this field.
 	//
 	// +optional
-	//nolint:kubeapilinter // ignore kubeapilinter here as we want to use pointer for optional struct.
-	PortNumber *PortNumber `json:"portNumber,omitempty"`
+	Port *Port `json:"port,omitempty"`
 
 	// FailureMode configures how the parent handles the case when the Endpoint Picker extension
 	// is non-responsive. When unspecified, defaults to "FailClose".
 	//
 	// +optional
 	// +kubebuilder:default="FailClose"
-	//nolint:kubeapilinter // ignore kubeapilinter here as we want to use pointer for optional struct.
-	FailureMode *EndpointPickerFailureMode `json:"failureMode,omitempty"`
+	FailureMode EndpointPickerFailureMode `json:"failureMode,omitempty"`
 }
 
 // EndpointPickerFailureMode defines the options for how the parent handles the case when the
@@ -286,8 +287,7 @@ type ParentReference struct {
 	//
 	// +optional
 	// +kubebuilder:default=Gateway
-	//nolint:kubeapilinter // ignore kubeapilinter here as we want to use pointer for optional struct.
-	Kind *Kind `json:"kind,omitempty"`
+	Kind Kind `json:"kind,omitempty"`
 
 	// Name is the name of the referent API object.
 	//
@@ -303,6 +303,5 @@ type ParentReference struct {
 	// documentation for details: https://gateway-api.sigs.k8s.io/api-types/referencegrant/
 	//
 	// +optional
-	//nolint:kubeapilinter // ignore kubeapilinter here as we want to use pointer for optional struct.
-	Namespace *Namespace `json:"namespace,omitempty"`
+	Namespace Namespace `json:"namespace,omitempty"`
 }

api/v1/zz_generated.deepcopy.go

@@ -25,7 +25,6 @@ import (
 // +kubebuilder:object:root=true
 // +kubebuilder:subresource:status
 // +kubebuilder:storageversion
-// +kubebuilder:printcolumn:name="Model Name",type=string,JSONPath=`.spec.modelName`
 // +kubebuilder:printcolumn:name="Inference Pool",type=string,JSONPath=`.spec.poolRef.name`
 // +kubebuilder:printcolumn:name="Priority",type=string,JSONPath=`.spec.priority`
 // +kubebuilder:printcolumn:name="Age",type=date,JSONPath=`.metadata.creationTimestamp`
@@ -56,12 +55,6 @@ type InferenceObjectiveList struct {
 // performance and latency goals for the model. These workloads are
 // expected to operate within an InferencePool sharing compute capacity with other
 // InferenceObjectives, defined by the Inference Platform Admin.
-//
-// InferenceObjective'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
-// InferenceObjective that attempted to reuse. The oldest InferenceObjective, based on
-// creation timestamp, will be selected to remain valid. In the event of a race
-// condition, one will be selected at random.
 type InferenceObjectiveSpec struct {
 
 	// Priority defines how important it is to serve the request compared to other requests in the same pool.
@@ -135,10 +128,6 @@ const (
 	//
 	// * "Accepted"
 	//
-	// Possible reasons for this condition to be False are:
-	//
-	// * "ModelNameInUse"
-	//
 	// Possible reasons for this condition to be Unknown are:
 	//
 	// * "Pending"
@@ -148,10 +137,6 @@ const (
 	// ObjectiveReasonAccepted is the desired state. Model conforms to the state of the pool.
 	ObjectiveReasonAccepted InferenceObjectiveConditionReason = "Accepted"
 
-	// ObjectiveReasonNameInUse is used when a given ModelName already exists within the pool.
-	// Details about naming conflict resolution are on the ModelName field itself.
-	ObjectiveReasonNameInUse InferenceObjectiveConditionReason = "ModelNameInUse"
-
 	// ObjectiveReasonPending is the initial state, and indicates that the controller has not yet reconciled the InferenceObjective.
 	ObjectiveReasonPending InferenceObjectiveConditionReason = "Pending"
 )