merge with main

Author: capri-xiyue

Dockerfile

@@ -22,8 +22,9 @@ COPY pkg/epp ./pkg/epp
 COPY internal ./internal
 COPY apix ./apix
 COPY api ./api
+COPY version ./version
 WORKDIR /src/cmd/epp
-RUN go build -ldflags="-X sigs.k8s.io/gateway-api-inference-extension/pkg/epp/metrics.CommitSHA=${COMMIT_SHA} -X sigs.k8s.io/gateway-api-inference-extension/pkg/epp/metrics.BuildRef=${BUILD_REF}" -o /epp
+RUN go build -ldflags="-X sigs.k8s.io/gateway-api-inference-extension/version.CommitSHA=${COMMIT_SHA} -X sigs.k8s.io/gateway-api-inference-extension/version.BuildRef=${BUILD_REF}" -o /epp
 
 ## Multistage deploy
 FROM ${BASE_IMAGE}

Makefile

@@ -95,12 +95,8 @@ help: ## Display this help.
 
 ##@ Development
 
-.PHONY: manifests
-manifests: controller-gen ## Generate WebhookConfiguration, ClusterRole and CustomResourceDefinition objects.
-	$(CONTROLLER_GEN) rbac:roleName=manager-role crd webhook paths="./..." output:crd:artifacts:config=config/crd/bases
-
 .PHONY: generate
-generate: controller-gen code-generator manifests ## Generate code containing DeepCopy, DeepCopyInto, and DeepCopyObject method implementations.
+generate: controller-gen code-generator ## Generate WebhookConfiguration, ClusterRole, CustomResourceDefinition objects, code containing DeepCopy, DeepCopyInto, and DeepCopyObject method implementations.
 	$(CONTROLLER_GEN) object:headerFile="hack/boilerplate/boilerplate.generatego.txt" paths="./..."
 	./hack/update-codegen.sh
 
@@ -132,7 +128,7 @@ vet: ## Run go vet against code.
 	go vet ./...
 
 .PHONY: test
-test: manifests generate fmt vet envtest image-build ## Run tests.
+test: generate fmt vet envtest image-build verify-crds ## Run tests.
 	CGO_ENABLED=1 KUBEBUILDER_ASSETS="$(shell $(ENVTEST) use $(ENVTEST_K8S_VERSION) --bin-dir $(LOCALBIN) -p path)" go test $$(go list ./... | grep -v /e2e | grep -v /conformance) -race -coverprofile cover.out
 
 .PHONY: test-unit
@@ -160,9 +156,13 @@ ci-lint: golangci-lint
 	$(GOLANGCI_LINT) run --timeout 15m0s
 
 .PHONY: verify
-verify: vet fmt-verify manifests generate ci-lint verify-all
+verify: vet fmt-verify generate ci-lint verify-all
 	git --no-pager diff --exit-code config api client-go
 
+.PHONY: verify-crds
+verify-crds: kubectl-validate
+	hack/verify-manifests.sh
+
 # Run static analysis.
 .PHONY: verify-all
 verify-all:
@@ -307,11 +307,11 @@ ifndef ignore-not-found
 endif
 
 .PHONY: install
-install: manifests kustomize ## Install CRDs into the K8s cluster specified in ~/.kube/config.
+install: generate kustomize ## Install CRDs into the K8s cluster specified in ~/.kube/config.
 	$(KUSTOMIZE) build config/crd | $(KUBECTL) apply -f -
 
 .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.
+uninstall: generate 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.
 	$(KUSTOMIZE) build config/crd | $(KUBECTL) delete --ignore-not-found=$(ignore-not-found) -f -
 
 ##@ Helm
@@ -354,13 +354,15 @@ ENVTEST ?= $(LOCALBIN)/setup-envtest
 GOLANGCI_LINT = $(LOCALBIN)/golangci-lint
 HELM = $(PROJECT_DIR)/bin/helm
 YQ = $(PROJECT_DIR)/bin/yq
+KUBECTL_VALIDATE = $(PROJECT_DIR)/bin/kubectl-validate
 
 ## Tool Versions
 KUSTOMIZE_VERSION ?= v5.4.3
 CONTROLLER_TOOLS_VERSION ?= v0.16.1
 ENVTEST_VERSION ?= release-0.19
 GOLANGCI_LINT_VERSION ?= v1.62.2
 HELM_VERSION ?= v3.17.1
+KUBECTL_VALIDATE_VERSION ?= v0.0.4
 
 .PHONY: kustomize
 kustomize: $(KUSTOMIZE) ## Download kustomize locally if necessary.
@@ -390,6 +392,11 @@ yq: ## Download yq locally if necessary.
 helm: ## Download helm locally if necessary.
 	GOBIN=$(PROJECT_DIR)/bin GO111MODULE=on go install helm.sh/helm/v3/cmd/helm@$(HELM_VERSION)
 
+.PHONY: kubectl-validate
+kubectl-validate: $(KUBECTL_VALIDATE) ## Download kubectl-validate locally if necessary.
+$(KUBECTL_VALIDATE): $(LOCALBIN)
+	$(call go-install-tool,$(KUBECTL_VALIDATE),sigs.k8s.io/kubectl-validate,$(KUBECTL_VALIDATE_VERSION))
+
 # go-install-tool will 'go install' any package with custom target and name of binary, if it doesn't exist
 # $1 - target path with name of binary
 # $2 - package url which can be installed

RELEASE.md

@@ -7,4 +7,4 @@ The Kubernetes Template Project is released on an as-needed basis. The process i
 1. All [OWNERS](OWNERS) must LGTM this release
 1. An OWNER runs `git tag -s $VERSION` and inserts the changelog and pushes the tag with `git push $VERSION`
 1. The release issue is closed
-1. An announcement email is sent to `[email protected]` with the subject `[ANNOUNCE] kubernetes-template-project $VERSION is released`
+1. An announcement email is sent to `[email protected]` with the subject `[ANNOUNCE] kubernetes-template-project $VERSION is released`

cmd/epp/runner/runner.go

@@ -48,6 +48,7 @@ import (
 	"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/scheduling"
 	runserver "sigs.k8s.io/gateway-api-inference-extension/pkg/epp/server"
 	"sigs.k8s.io/gateway-api-inference-extension/pkg/epp/util/logging"
+	"sigs.k8s.io/gateway-api-inference-extension/version"
 )
 
 var (
@@ -197,6 +198,8 @@ func (r *Runner) Run(ctx context.Context) error {
 	flag.Parse()
 	initLogging(&opts)
 
+	setupLog.Info("GIE build", "commit-sha", version.CommitSHA, "build-ref", version.BuildRef)
+
 	// Validate flags
 	if err := validateFlags(); err != nil {
 		setupLog.Error(err, "Failed to validate flags")
@@ -242,7 +245,7 @@ func (r *Runner) Run(ctx context.Context) error {
 	// --- Setup Metrics Server ---
 	customCollectors := []prometheus.Collector{collectors.NewInferencePoolMetricsCollector(datastore)}
 	metrics.Register(customCollectors...)
-	metrics.RecordInferenceExtensionInfo()
+	metrics.RecordInferenceExtensionInfo(version.CommitSHA, version.BuildRef)
 	// Register metrics handler.
 	// Metrics endpoint is enabled in 'config/default/kustomization.yaml'. The Metrics options configure the server.
 	// More info:

config/crd/bases/inference.networking.k8s.io_inferencepools.yaml

@@ -1,10 +1,10 @@
----
 apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
     api-approved.kubernetes.io: unapproved, experimental-only
-    controller-gen.kubebuilder.io/version: v0.16.1
+    inference.networking.k8s.io/bundle-version: v1.0.0-dev
+  creationTimestamp: null
   name: inferencepools.inference.networking.k8s.io
 spec:
   group: inference.networking.k8s.io
@@ -284,3 +284,9 @@ spec:
     storage: true
     subresources:
       status: {}
+status:
+  acceptedNames:
+    kind: ""
+    plural: ""
+  conditions: null
+  storedVersions: null

config/crd/bases/inference.networking.x-k8s.io_inferencemodels.yaml

@@ -1,9 +1,9 @@
----
 apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.16.1
+    inference.networking.k8s.io/bundle-version: v1.0.0-dev
+  creationTimestamp: null
   name: inferencemodels.inference.networking.x-k8s.io
 spec:
   group: inference.networking.x-k8s.io
@@ -254,3 +254,9 @@ spec:
     storage: true
     subresources:
       status: {}
+status:
+  acceptedNames:
+    kind: ""
+    plural: ""
+  conditions: null
+  storedVersions: null

config/crd/bases/inference.networking.x-k8s.io_inferencepools.yaml

@@ -1,10 +1,10 @@
----
 apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
     api-approved.kubernetes.io: unapproved, experimental-only
-    controller-gen.kubebuilder.io/version: v0.16.1
+    inference.networking.k8s.io/bundle-version: v1.0.0-dev
+  creationTimestamp: null
   name: inferencepools.inference.networking.x-k8s.io
 spec:
   group: inference.networking.x-k8s.io
@@ -284,3 +284,9 @@ spec:
     storage: true
     subresources:
       status: {}
+status:
+  acceptedNames:
+    kind: ""
+    plural: ""
+  conditions: null
+  storedVersions: null

config/manifests/vllm/cpu-deployment.yaml

@@ -14,7 +14,7 @@ spec:
     spec:
       containers:
         - name: lora
-          image: "public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v0.9.1" # formal images can be found in https://gallery.ecr.aws/q9t5s3a7/vllm-cpu-release-repo
+          image: "public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:latest" # formal images can be found in https://gallery.ecr.aws/q9t5s3a7/vllm-cpu-release-repo
           imagePullPolicy: Always
           command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
           args:

hack/release-quickstart.sh

@@ -42,6 +42,21 @@ echo "Using vLLM GPU image version: ${VLLM_GPU}"
 echo "Using vLLM CPU image version: ${VLLM_CPU}"
 echo "Using vLLM Simulator image version: ${VLLM_SIM}"
 
+# -----------------------------------------------------------------------------
+# Update version/version.go and generating CRDs with new version annotations
+# -----------------------------------------------------------------------------
+VERSION_FILE="version/version.go"
+echo "Updating ${VERSION_FILE} ..."
+
+# Replace bundleVersion in version.go
+# This regex finds the line with "BundleVersion" and replaces the string within the quotes.
+sed -i.bak -E "s|( *BundleVersion = \")[^\"]+(\")|\1${RELEASE_TAG}\2|g" "$VERSION_FILE"
+
+UPDATED_CRD="config/crd/"
+echo "Generating CRDs with new annotations in $UPDATED_CRD"
+go run ./pkg/generator
+echo "Generated CRDs with new annotations in $UPDATED_CRD"
+
 # -----------------------------------------------------------------------------
 # Update pkg/README.md
 # -----------------------------------------------------------------------------
@@ -63,20 +78,24 @@ EPP="config/manifests/inferencepool-resources.yaml"
 #TODO: Put all helm values files into an array to loop over
 EPP_HELM="config/charts/inferencepool/values.yaml"
 BBR_HELM="config/charts/body-based-routing/values.yaml"
-echo "Updating ${EPP} & ${EPP_HELM} ..."
+CONFORMANCE_MANIFESTS="conformance/resources/manifests/manifests.yaml"
+echo "Updating ${EPP}, ${EPP_HELM}, ${BBR_HELM}, and ${CONFORMANCE_MANIFESTS} ..."
 
 # Update the container tag.
 sed -i.bak -E "s|(us-central1-docker\.pkg\.dev/k8s-staging-images/gateway-api-inference-extension/epp:)[^\"[:space:]]+|\1${RELEASE_TAG}|g" "$EPP"
 sed -i.bak -E "s|(tag: )[^\"[:space:]]+|\1${RELEASE_TAG}|g" "$EPP_HELM"
 sed -i.bak -E "s|(tag: )[^\"[:space:]]+|\1${RELEASE_TAG}|g" "$BBR_HELM"
+sed -i.bak -E "s|(us-central1-docker\.pkg\.dev/k8s-staging-images/gateway-api-inference-extension/epp:)[^\"[:space:]]+|\1${RELEASE_TAG}|g" "$CONFORMANCE_MANIFESTS"
 
 # Update the container image pull policy.
 sed -i.bak '/us-central1-docker.pkg.dev\/k8s-staging-images\/gateway-api-inference-extension\/epp/{n;s/Always/IfNotPresent/;}' "$EPP"
+sed -i.bak '/us-central1-docker.pkg.dev\/k8s-staging-images\/gateway-api-inference-extension\/epp/{n;s/Always/IfNotPresent/;}' "$CONFORMANCE_MANIFESTS"
 
 # Update the container registry.
 sed -i.bak -E "s|us-central1-docker\.pkg\.dev/k8s-staging-images|registry.k8s.io|g" "$EPP"
 sed -i.bak -E "s|us-central1-docker\.pkg\.dev/k8s-staging-images|registry.k8s.io|g" "$EPP_HELM"
 sed -i.bak -E "s|us-central1-docker\.pkg\.dev/k8s-staging-images|registry.k8s.io|g" "$BBR_HELM"
+sed -i.bak -E "s|us-central1-docker\.pkg\.dev/k8s-staging-images|registry.k8s.io|g" "$CONFORMANCE_MANIFESTS"
 
 # -----------------------------------------------------------------------------
 # Update vLLM deployment manifests
@@ -111,8 +130,8 @@ sed -i.bak '/llm-d\/llm-d-inference-sim/{n;s/Always/IfNotPresent/;}' "$VLLM_SIM_
 # -----------------------------------------------------------------------------
 # Stage the changes
 # -----------------------------------------------------------------------------
-echo "Staging $README $EPP $EPP_HELM $BBR_HELM $VLLM_GPU_DEPLOY $VLLM_CPU_DEPLOY $VLLM_SIM_DEPLOY files..."
-git add $README $EPP $EPP_HELM $BBR_HELM $VLLM_GPU_DEPLOY $VLLM_CPU_DEPLOY $VLLM_SIM_DEPLOY
+echo "Staging $VERSION_FILE $UPDATED_CRD $README $EPP $EPP_HELM $BBR_HELM $CONFORMANCE_MANIFESTS $VLLM_GPU_DEPLOY $VLLM_CPU_DEPLOY $VLLM_SIM_DEPLOY files..."
+git add $VERSION_FILE $UPDATED_CRD $README $EPP $EPP_HELM $BBR_HELM $CONFORMANCE_MANIFESTS $VLLM_GPU_DEPLOY $VLLM_CPU_DEPLOY $VLLM_SIM_DEPLOY
 
 # -----------------------------------------------------------------------------
 # Cleanup backup files and finish

hack/update-codegen.sh

@@ -18,6 +18,9 @@ set -o errexit
 set -o nounset
 set -o pipefail
 
+echo "Generating CRDs"
+go run ./pkg/generator
+
 SCRIPT_ROOT=$(dirname "${BASH_SOURCE[0]}")/..
 echo "$SCRIPT_ROOT script"
 CODEGEN_PKG=${2:-bin}