sync to upstream

Author: geodavic

.flake8

@@ -0,0 +1,2 @@
+*.sh linguist-vendored
+python/kserve/kserve/models/** linguist-generated=true

.gitattributes

@@ -4,25 +4,19 @@
 3. If you want *faster* PR reviews, read how: https://git.k8s.io/community/contributors/guide/pull-requests.md#best-practices-for-faster-reviews
 4. Follow the instructions for writing a release note: https://git.k8s.io/community/contributors/guide/release-notes.md
 5. If the PR is unfinished, see how to mark it: https://git.k8s.io/community/contributors/guide/pull-requests.md#marking-unfinished-pull-requests
+6. Re-running failed tests: comment `/rerun-all` to rerun all failed workflows.
 -->
 
 **What this PR does / why we need it**:
 
 **Which issue(s) this PR fixes** *(optional, in `fixes #<issue number>(, fixes #<issue_number>, ...)` format, will close the issue(s) when PR gets merged)*:
 Fixes #
 
-**Type of changes**
-Please delete options that are not relevant.
-
-- [ ] Bug fix (non-breaking change which fixes an issue)
-- [ ] New feature (non-breaking change which adds functionality)
-- [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
-- [ ] This change requires a documentation update
 
 **Feature/Issue validation/testing**:
 
-Please describe the tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced.
-Please also list any relevant details for your test configuration.
+<!--Please describe the tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced.
+Please also list any relevant details for your test configuration. -->
 
 - [ ] Test A
 - [ ] Test B
@@ -31,13 +25,13 @@ Please also list any relevant details for your test configuration.
 
 **Special notes for your reviewer**:
 
-1. Please confirm that if this PR changes any image versions, then that's the sole change this PR makes.
+<!-- 1. Please confirm that if this PR changes any image versions, then that's the sole change this PR makes. -->
 
 **Checklist**:
 
 - [ ] Have you added unit/e2e tests that prove your fix is effective or that this feature works?
 - [ ] Has code been commented, particularly in hard-to-understand areas?
-- [ ] Have you made corresponding changes to the documentation?
+- [ ] Have you made corresponding changes to the [documentation](https://github.com/kserve/website)?
 
 **Release note**:
 <!--  Write your release note:
@@ -47,8 +41,3 @@ Please also list any relevant details for your test configuration.
 ```release-note
 
 ```
-
-**Re-running failed tests**
-
-- `/rerun-all` - rerun all failed workflows.
-- `/rerun-workflow <workflow name>` - rerun a specific failed workflow. Only one workflow name can be specified. Multiple /rerun-workflow commands are allowed per comment.

.github/PULL_REQUEST_TEMPLATE.md

@@ -13,21 +13,20 @@ inputs:
     description: 'Enable KEDA for autoscaling'
     required: false
     default: 'false'
+  deploy-llmisvc:
+    description: 'Deploy LLM Inference Service Controller'
+    required: false
+    default: 'false'    
 runs:
   using: "composite"
   steps:
     - name: Setup KServe dependencies
       shell: bash
       run: |
-        shopt -s nocasematch 
-
-        if [[ "${{ inputs.network-layer }}" == "kourier" ]]; then
-          echo "Selected network layer ${{ inputs.network-layer }}"
-          ./test/scripts/gh-actions/setup-kourier.sh
-        else
-          echo "Selected network layer ${{ inputs.network-layer }}"
-          ./test/scripts/gh-actions/setup-deps.sh ${{ inputs.deployment-mode }} "${{ inputs.network-layer }}" "${{ inputs.enable-keda }}"
-        fi
+        shopt -s nocasematch         
+        echo "Selected network layer ${{ inputs.network-layer }}"
+        ./test/scripts/gh-actions/setup-deps.sh ${{ inputs.deployment-mode }} "${{ inputs.network-layer }}" "${{ inputs.enable-keda }}" "${{ inputs.deploy-llmisvc }}"
+      
 
     - name: Update test overlays
       shell: bash

.github/actions/kserve-dep-setup/action.yml

@@ -0,0 +1,149 @@
+name: LLMInferenceService E2E Tests
+
+on:
+  pull_request:
+    paths:
+      - "pkg/apis/serving/v1alpha1/llm*"
+      - "pkg/apis/serving/v1alpha2/llm*"
+      - "pkg/controller/v1alpha1/llmisvc/**"
+      - "pkg/controller/v1alpha2/llmisvc/**"
+      - "charts/kserve-llmisvc-resources/**"
+      - "config/llmisvc/**"
+      - "config/rbac/llmisvc/**"
+      - "cmd/llmisvc/**"
+      - "test/e2e/llmisvc/**"
+      - ".github/workflows/e2e-test-llmisvc.yaml"
+      - "hack/setup/quick-install/llmisvc-dependency-install.sh"
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+  TAG: ${{ github.sha }}
+  DOCKER_IMAGES_PATH: "/mnt/docker-images"
+  KO_DOCKER_REPO: "kserve"
+  LLMISVC: "true"
+
+jobs:
+  
+  llmisvc-image-build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout source
+        uses: actions/checkout@v4
+
+      - name: Load KServe environment variables
+        run: ./kserve-images.sh --ci
+
+      - name: Free-up disk space
+        uses: ./.github/actions/free-up-disk-space
+
+      - name: Setup Docker Buildx
+        uses: docker/setup-buildx-action@v3
+        with:
+          cache-binary: true
+          
+      - name: Build LLMISvc image
+        run: |
+          sudo mkdir -p ${DOCKER_IMAGES_PATH}
+          sudo chown -R $USER ${DOCKER_IMAGES_PATH}
+          ./test/scripts/gh-actions/build-images.sh llmisvc
+          docker image ls
+          sudo ls -lh ${DOCKER_IMAGES_PATH}
+      
+      - name: Upload LLMISvc controller image
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ env.LLMISVC_CONTROLLER_IMG }}-${{ env.TAG }}
+          path: ${{ env.DOCKER_IMAGES_PATH }}/${{ env.LLMISVC_CONTROLLER_IMG }}-${{ env.TAG }}
+          compression-level: 0
+          if-no-files-found: error
+          
+  test-llmisvc:
+    runs-on: ubuntu-latest
+    needs: [llmisvc-image-build]
+    steps:
+      - name: Checkout source
+        uses: actions/checkout@v4
+
+      - name: Load KServe environment variables
+        run: ./kserve-images.sh --ci
+        
+      - name: Free-up disk space
+        uses: ./.github/actions/free-up-disk-space
+
+      - name: Setup Go
+        uses: actions/setup-go@v5
+        with:
+          go-version-file: go.mod
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.9"
+
+      - name: Setup Minikube
+        uses: ./.github/actions/minikube-setup
+          
+      - name: Download LLMISvc controller image
+        uses: actions/download-artifact@v4
+        with:
+          name: ${{ env.LLMISVC_CONTROLLER_IMG }}-${{ env.TAG }}
+          path: ./tmp
+
+      - name: Load LLMISvc controller image into minikube
+        run: |          
+          # Load the tagged image into minikube
+          minikube image load ./tmp/${{ env.LLMISVC_CONTROLLER_IMG }}-${{ env.TAG }}
+
+          # Verify image is loaded
+          echo "Images in minikube:"
+          minikube image ls | grep ${{ env.LLMISVC_CONTROLLER_IMG }} || echo "No llmisvc-controller images found"
+
+      - name: KServe dependency setup
+        uses: ./.github/actions/kserve-dep-setup
+        with:
+          deploy-llmisvc: "true"
+
+      - name: Install UV
+        run: ./test/scripts/gh-actions/setup-uv.sh
+
+      - name: Install KServe
+        run: |          
+          ./test/scripts/gh-actions/setup-kserve.sh
+
+      - name: Verify LLMISvc setup
+        run: |
+          echo "🔍 Verifying LLMISvc controller setup..."
+
+          echo "📋 LLMISvc Controller:"
+          kubectl get pods -n kserve -l app.kubernetes.io/component=controller || true
+
+          echo "📋 LLM Resources:"
+          kubectl get llminferenceserviceconfigs -A || true
+
+          echo "📋 Gateway API Resources:"
+          kubectl get crd | grep inference || true
+
+          echo "📋 Envoy Gateway:"
+          kubectl get pods -n envoy-gateway-system || true
+
+          echo "📋 AI Gateway:"
+          kubectl get pods -n envoy-ai-gateway-system || true
+
+          echo "✅ LLMISvc setup verification complete!"
+
+      - name: Run predictor E2E tests
+        id: predictor-tests
+        timeout-minutes: 40
+        run: |
+          # Run only CPU tests for now using pytest markers (cluster_)
+          # Available GPU vendors: amd, nvidia, intel
+          ./test/scripts/gh-actions/run-e2e-tests.sh "llminferenceservice and cluster_cpu" 1 "envoy-gateway"
+       
+      - name: Check system status
+        if: always()
+        run: |
+          ./test/scripts/gh-actions/status-check.sh "llmisvc"