Fix in scorer manager in picking the best target

.tekton/deploy-infra-to-openshift.yaml

@@ -0,0 +1,88 @@
+apiVersion: tekton.dev/v1
+kind: Task
+metadata:
+  name: openshift-redeploy-infra-task
+spec:
+  params:
+    - name: source-branch
+      type: string
+      description: "Git branch name"
+    - name: prod-version
+      type: string
+    - name: dev-version
+      type: string
+    - name: prod_image_tag_base
+      type: string
+    - name: dev_image_tag_base
+      type: string
+  workspaces:
+    - name: source
+  steps:
+  - name: redeploy
+    image: quay.io/projectquay/golang:1.24
+    imagePullPolicy: IfNotPresent
+    securityContext:
+      privileged: true
+    workingDir: $(workspaces.source.path)
+    env:
+      - name: STORAGE_DRIVER
+        value: vfs
+    script: |
+      #!/bin/bash
+      set -e
+
+      echo "📦 Installing dependencies with dnf..."
+      dnf install -y make jq curl gettext && dnf clean all
+
+      echo "📥 Installing kubectl..."
+      curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl"
+      install -o root -g root -m 0755 kubectl /usr/local/bin/kubectl
+
+      echo "📥 Installing kustomize..."
+      KUSTOMIZE_TAG=$(curl -s https://api.github.com/repos/kubernetes-sigs/kustomize/releases/latest | jq -r '.tag_name')
+      KUSTOMIZE_VERSION="${KUSTOMIZE_TAG##*/}"  # strips prefix like 'kustomize/' from tag
+
+      curl -LO "https://github.com/kubernetes-sigs/kustomize/releases/download/${KUSTOMIZE_TAG}/kustomize_${KUSTOMIZE_VERSION}_linux_amd64.tar.gz"
+
+      tar -xzf "kustomize_${KUSTOMIZE_VERSION}_linux_amd64.tar.gz" -C /usr/local/bin
+      chmod +x /usr/local/bin/kustomize
+      kustomize version
+
+      echo "🔧 Getting namespace and project_name from Makefile..."
+      DEFAULT_NAMESPACE=$(make -s print-namespace)
+      PROJECT_NAME=$(make -s print-project-name)
+
+      if [ "$(params.source-branch)" = "main" ]; then
+        NS="${DEFAULT_NAMESPACE}"
+        IMAGE_TAG_BASE=$(params.prod_image_tag_base)
+        VERSION=$(params.prod-version)
+      else
+        NS="${DEFAULT_NAMESPACE}-dev"
+        IMAGE_TAG_BASE=$(params.dev_image_tag_base)
+        VERSION=$(params.dev-version)
+      fi
+
+      echo "🔧 Using namespace: $NS"
+      echo "🔧 Using project_name: $PROJECT_NAME"
+      echo "🔧 Using image_tag_base: $IMAGE_TAG_BASE"
+      echo "🔧 Using version: $VERSION"
+
+      # echo "🧹 Uninstalling existing deployment..."
+      # # make uninstall-openshift NAMESPACE=$NS PROJECT_NAME=$PROJECT_NAME IMAGE_TAG_BASE=$IMAGE_TAG_BASE VERSION=$VERSION || echo "❗️ Failed to uninstall deployment"
+
+      # (make uninstall || echo "❗️ Failed to uninstall") && (make undeploy IMG=$IMAGE_TAG_BASE:$VERSION || echo "❗️ Failed to uninstall deployment")
+
+      # echo "⏳ Waiting 3 seconds before reinstall..."
+      # sleep 3
+
+      echo "🚀 Reinstalling OpenShift deployment..."
+      INFRASTRUCTURE_OVERRIDE=true make install-openshift-infrastructure
+
+      echo "⏳ Waiting 20 seconds before verifying resources..."
+      sleep 20
+
+      echo "🔍 Checking status of resources in namespace: $NS"
+      kubectl get pods -n $NS || echo "❗️ Failed to get pods"
+      kubectl get deploy -n $NS || echo "❗️ Failed to get deployments"
+      kubectl get svc -n $NS || echo "❗️ Failed to get services"
+      kubectl get routes -n $NS || echo "❗️ Failed to get routes"

.tekton/infra-pipelinerun.yaml

@@ -0,0 +1,182 @@
+apiVersion: tekton.dev/v1
+kind: PipelineRun
+metadata:
+  name: modelservice-infra
+  annotations:
+    pipelinesascode.tekton.dev/on-event: "[push]"
+    pipelinesascode.tekton.dev/on-target-branch: "[infra]"
+    pipelinesascode.tekton.dev/task: "git-clone"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
+    pipelinesascode.tekton.dev/git-status: "true"
+    pipelinesascode.tekton.dev/on-cel-expression: >
+      (!has(body.ref) || body.ref == 'refs/heads/infra') &&
+      (!has(body.head_commit) || !has(body.head_commit.author) || !body.head_commit.author.name.matches("(?i).*ci-tag-bot.*")) &&
+      (!has(body.pull_request) || body.pull_request.base.ref == 'infra')
+spec:
+  podTemplate:
+    serviceAccountName: pipeline
+    securityContext:
+      fsGroup: 0
+    imagePullSecrets:
+      - name: icr-secret
+  params:
+    - name: runOptional
+      value: "true"
+    - name: repo_url
+      value: "{{ repo_url }}"
+    - name: revision
+      value: "{{ revision }}"
+    - name: deleteExisting
+      value: "true"
+    - name: source_branch
+      value: "{{ source_branch }}"
+  pipelineSpec:
+    params:
+      - name: repo_url
+      - name: revision
+      - name: deleteExisting
+      - name: source_branch
+    workspaces:
+      - name: source
+      - name: basic-auth
+      - name: git-auth
+      - name: registry-secret
+    tasks:
+      - name: fix-permissions
+        taskSpec:
+          workspaces:
+            - name: source
+              workspace: source
+          steps:
+            - name: fix
+              image: quay.io/projectquay/golang:1.24
+              script: |
+                #!/bin/sh
+                echo "Fixing permissions on /workspace/source..."
+                chmod -R 777 /workspace/source || true
+        workspaces:
+          - name: source
+            workspace: source
+
+      - name: which-branch
+        taskRef:
+          name: print-branch-task
+        runAfter:
+          - fix-permissions
+        params:
+          - name: source-branch
+            value: "$(params.source_branch)"
+        workspaces:
+          - name: source
+            workspace: source
+
+      - name: fetch-repository
+        taskRef:
+          name: git-clone
+        runAfter:
+          - which-branch
+        workspaces:
+          - name: output
+            workspace: source
+          - name: basic-auth
+            workspace: basic-auth
+        params:
+          - name: url
+            value: $(params.repo_url)
+          - name: revision
+            value: $(params.revision)
+          - name: deleteExisting
+            value: "$(params.deleteExisting)"
+
+      - name: extract-version-and-registry
+        params:
+          - name: source-branch  
+            value: "$(params.source_branch)"
+        runAfter:
+          - fetch-repository
+        taskRef:
+          name: extract-version-and-registry-task
+        workspaces:
+          - name: source
+            workspace: source
+
+      - name: tag-version
+        when:
+          - input: "$(params.runOptional)"
+            operator: in
+            values: ["true"]
+          - input: "$(params.source_branch)"
+            operator: in
+            values: ["infra"]
+        taskRef:
+          name: tag-version-task
+        params:
+          - name: source-branch
+            value: "$(params.source_branch)"
+          - name: prod-version
+            value: "$(tasks.extract-version-and-registry.results.prod-version)"
+          - name: dev-version
+            value: "$(tasks.extract-version-and-registry.results.dev-version)"
+        runAfter:
+          - extract-version-and-registry
+        workspaces:
+          - name: source
+            workspace: source
+          - name: git-auth
+            workspace: git-auth
+
+      - name: openshift-redeploy
+        when:
+          - input: "$(params.runOptional)"
+            operator: in
+            values: ["true"]
+          - input: "$(params.source_branch)"
+            operator: in
+            values: ["infra"]
+        taskRef:
+          name: openshift-redeploy-infra-task
+        params:
+          - name: source-branch
+            value: "$(params.source_branch)"
+          - name: prod-version
+            value: "$(tasks.extract-version-and-registry.results.prod-version)"
+          - name: dev-version
+            value: "$(tasks.extract-version-and-registry.results.dev-version)"
+          - name: prod_image_tag_base
+            value: "$(tasks.extract-version-and-registry.results.prod-image-tag-base)"
+          - name: dev_image_tag_base
+            value: "$(tasks.extract-version-and-registry.results.dev-image-tag-base)"
+        runAfter:
+          - tag-version
+        workspaces:
+          - name: source
+            workspace: source
+
+      - name: pipeline-complete-infra
+        when:
+          - input: "$(params.source_branch)"
+            operator: in
+            values: ["infra"]
+        runAfter:
+          - openshift-redeploy
+        taskRef:
+          name: noop-task
+
+  workspaces:
+    - name: source
+      volumeClaimTemplate:
+        spec:
+          accessModes:
+            - ReadWriteOnce
+          resources:
+            requests:
+              storage: 1Gi
+    - name: basic-auth
+      secret:
+        secretName: "{{ git_auth_secret }}"
+    - name: git-auth  
+      secret:
+        secretName: "git-auth-secret-neuralmagic"
+    - name: registry-secret
+      secret:
+        secretName: quay-secret

.tekton/pipelinerun.yaml

@@ -6,7 +6,7 @@ metadata:
     pipelinesascode.tekton.dev/on-event: "[pull_request, push]"
     pipelinesascode.tekton.dev/on-target-branch: "[main, dev]"
     pipelinesascode.tekton.dev/task: "git-clone"
-    pipelinesascode.tekton.dev/max-keep-runs: "5"
+    pipelinesascode.tekton.dev/max-keep-runs: "3"
     pipelinesascode.tekton.dev/git-status: "true"
     pipelinesascode.tekton.dev/on-cel-expression: >
       (!has(body.ref) || body.ref == 'refs/heads/main' || body.ref == 'refs/heads/dev') &&

.version.json

@@ -1,6 +1,6 @@
 {
-  "dev-version": "0.0.2",
+  "dev-version": "0.0.3",
   "dev-registry": "quay.io/vllm-d/gateway-api-inference-extension-dev",
-  "prod-version": "0.0.1",
+  "prod-version": "0.0.2",
   "prod-registry": "quay.io/vllm-d/gateway-api-inference-extension"
 }

DEVELOPMENT.md

@@ -0,0 +1,73 @@
+# Development
+
+Developing and testing the Gateway API Inference Extension (GIE) is done by
+building your Endpoint Picker (EPP) image and attaching that to a `Gateway` on a
+development cluster, with some model serving backend to route traffic to.
+
+We provide `Makefile` targets and development environment deployment manifests
+under the `deploy/environments` directory, which include support for
+multiple kinds of clusters:
+
+* Kubernetes In Docker (KIND)
+* Kubernetes (WIP: https://github.com/neuralmagic/gateway-api-inference-extension/issues/14)
+* OpenShift (WIP: https://github.com/neuralmagic/gateway-api-inference-extension/issues/22)
+
+We support multiple different model serving platforms for testing:
+
+* VLLM
+* VLLM-Simulator
+
+In the following sections we will cover how to use the different development
+environment options.
+
+## Kubernetes In Docker (KIND)
+
+A [KIND] cluster can be used for basic development and testing on a local
+system. This environment will generally be limited to using a model serving
+simulator and as such is very limited compared to clusters with full model
+serving resources.
+
+[KIND]:https://github.com/kubernetes-sigs/kind
+
+### Setup
+
+> **WARNING**: This current requires you to have manually built the vllm
+> simulator separately on your local system. In a future iteration this will
+> be handled automatically and will not be required.
+
+Run the following:
+
+```console
+make environment.dev.kind
+```
+
+This will create a `kind` cluster (or re-use an existing one) using the system's
+local container runtime and deploy the development stack into the `default`
+namespace. Instrutions will be provided on how to access the `Gateway` and send
+requests for testing.
+
+> **NOTE**: If you require significant customization of this environment beyond
+> what the standard deployment provides, you can use the `deploy/components`
+> with `kustomize` to build your own highly customized environment. You can use
+> the `deploy/environments/kind` deployment as a reference for your own.
+
+#### Development Cycle
+
+To test your changes to the GIE in this environment, make your changes locally
+and then run the following:
+
+```console
+make environment.dev.kind.update
+```
+
+This will build images with your recent changes and load the new images to the
+cluster. Then a rollout the `Deployments` will be performed so that your
+recent changes are refleted.
+
+## Kubernetes
+
+WIP
+
+## OpenShift
+
+WIP

Dockerfile

@@ -33,6 +33,4 @@ WORKDIR /
 COPY --from=builder /workspace/bin/epp /app/epp
 USER 65532:65532
 
-CMD ["sleep", "infinity"]
-
-
+ENTRYPOINT ["/app/epp"]