[pull] master from kserve:master

.flake8

@@ -0,0 +1,18 @@
+[flake8]
+max-line-length = 120
+extend-ignore = E203,E501,E701, B017
+exclude =
+  .venv,
+  venv,
+  python/kserve/kserve/exceptions.py,
+  python/kserve/kserve/configuration.py,
+  python/kserve/kserve/rest.py,
+  python/kserve/kserve/api_client.py,
+  python/kserve/test/test_v1*.py,
+  python/kserve/kserve/__init__.py,
+  python/kserve/test/__init__.py,
+  python/kserve/test/test_knative*.py,
+  python/kserve/kserve/protocol/grpc/grpc_predict_v2*.py
+  python/*_pb2.py
+  docs/**/*.py
+  python/kserve/kserve/protocol/rest/openai/types/openapi.py

.github/PULL_REQUEST_TEMPLATE.md

@@ -46,3 +46,8 @@ 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/workflows/artexplainer-docker-publish.yml

@@ -27,17 +27,24 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v4
+      - name: Checkout source
+        uses: actions/checkout@v4
+
+      - name: Setup QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Setup Docker Buildx
+        uses: docker/setup-buildx-action@v3
 
       - name: Run tests
-        run: |
-          if [ -f docker-compose.test.yml ]; then
-            docker-compose --file docker-compose.test.yml build
-            docker-compose --file docker-compose.test.yml run sut
-          else
-            cd python
-            docker buildx build . --file artexplainer.Dockerfile
-          fi
+        uses: docker/build-push-action@v5
+        with:
+          platforms: linux/amd64, linux/arm64/v8
+          context: python
+          file: python/artexplainer.Dockerfile
+          push: false
+          # https://github.com/docker/buildx/issues/1533
+          provenance: false
 
   # Push image to GitHub Packages.
   # See also https://docs.docker.com/docker-hub/builds/
@@ -49,7 +56,8 @@ jobs:
     if: github.event_name == 'push'
 
     steps:
-      - uses: actions/checkout@v4
+      - name: Checkout source
+        uses: actions/checkout@v4
 
       - name: Setup QEMU
         uses: docker/setup-qemu-action@v3

.github/workflows/comment-cherry-pick.yml

@@ -0,0 +1,23 @@
+name: Cherry Pick On Comment
+
+on:
+  issue_comment:
+    types: [created]
+
+jobs:
+  cherry-pick:
+
+    name: Cherry Pick
+    if: github.event.issue.pull_request != '' && contains(github.event.comment.body, '/cherry-pick') && github.event.comment.author_association == 'CONTRIBUTOR'
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout the latest code
+        uses: actions/checkout@v2
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          fetch-depth: 0 # otherwise, you will fail to push refs to dest repo
+      - name: Automatic Cherry Pick
+        uses: hianhianhian/gha-cherry-pick@master
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/custom-model-grpc-publish.yml

@@ -26,15 +26,18 @@ jobs:
       - name: Checkout source
         uses: actions/checkout@v4
 
+      - name: Setup Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
       - name: Run tests
-        run: |
-          if [ -f docker-compose.test.yml ]; then
-            docker-compose --file docker-compose.test.yml build
-            docker-compose --file docker-compose.test.yml run sut
-          else
-            cd python
-            docker buildx build . --file custom_model_grpc.Dockerfile
-          fi
+        uses: docker/build-push-action@v5
+        with:
+          platforms: linux/amd64
+          context: python
+          file: python/custom_model_grpc.Dockerfile
+          push: false
+          # https://github.com/docker/buildx/issues/1533
+          provenance: false
 
   # Push image to GitHub Packages.
   # See also https://docs.docker.com/docker-hub/builds/
@@ -49,15 +52,16 @@ jobs:
       - name: Checkout source
         uses: actions/checkout@v4
 
-      - name: Build image
-        run: |
-          cd python
-          docker buildx build . --file custom_model_grpc.Dockerfile --tag $IMAGE_NAME
+      - name: Setup Docker Buildx
+        uses: docker/setup-buildx-action@v3
 
-      - name: Log into registry
-        run: docker login -u ${{ secrets.DOCKER_USER }} -p ${{ secrets.DOCKER_PASSWORD }}
+      - name: Login to DockerHub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USER }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
 
-      - name: Push image
+      - name: Export version variable
         run: |
           IMAGE_ID=kserve/$IMAGE_NAME
 
@@ -73,8 +77,16 @@ jobs:
           # Use Docker `latest` tag convention
           [ "$VERSION" == "master" ] && VERSION=latest
 
-          echo IMAGE_ID=$IMAGE_ID
-          echo VERSION=$VERSION
-
-          docker tag $IMAGE_NAME $IMAGE_ID:$VERSION
-          docker push $IMAGE_ID:$VERSION
+          echo VERSION=$VERSION >> $GITHUB_ENV
+          echo IMAGE_ID=$IMAGE_ID >> $GITHUB_ENV
+
+      - name: Build and push
+        uses: docker/build-push-action@v5
+        with:
+          platforms: linux/amd64
+          context: python
+          file: python/custom_model_grpc.Dockerfile
+          push: true
+          tags: ${{ env.IMAGE_ID }}:${{ env.VERSION }}
+          # https://github.com/docker/buildx/issues/1533
+          provenance: false

.github/workflows/e2e-test.yml

@@ -33,6 +33,7 @@ env:
   PMML_IMG: "pmmlserver"
   PADDLE_IMG: "paddleserver"
   CUSTOM_MODEL_GRPC_IMG: "custom-model-grpc"
+  HUGGINGFACE_IMG: "huggingfaceserver"
   # Explainer images
   ART_IMG: "art-explainer"
   # Transformer images
@@ -199,6 +200,14 @@ jobs:
           compression-level: 0
           if-no-files-found: error
 
+      - name: Upload huggingface image
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ env.HUGGINGFACE_IMG }}-${{ github.sha }}
+          path: ${{ env.DOCKER_IMAGES_PATH }}/${{ env.HUGGINGFACE_IMG }}-${{ github.sha }}
+          compression-level: 0
+          if-no-files-found: error
+
   explainer-runtime-build:
     runs-on: ubuntu-latest
     needs: [poetry-check]
@@ -847,3 +856,63 @@ jobs:
         if: always()
         run: |
           ./test/scripts/gh-actions/status-check.sh "kourier"
+
+  test-llm:
+    runs-on: ubuntu-latest
+    needs:
+      [ kserve-image-build, predictor-runtime-build]
+    steps:
+      - name: Checkout source
+        uses: actions/checkout@v4
+
+      - name: Free-up disk space
+        uses: ./.github/actions/free-up-disk-space
+
+      - name: Setup Go
+        uses: actions/setup-go@v5
+        with:
+          go-version: "1.21"
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.9"
+
+      - name: Setup Minikube
+        uses: ./.github/actions/minikube-setup
+
+      - name: KServe dependency setup
+        uses: ./.github/actions/kserve-dep-setup
+
+      - name: Download base images
+        uses: ./.github/actions/base-download
+
+      - name: Download huggingface server image
+        uses: actions/download-artifact@v4
+        with:
+          name: ${{ env.HUGGINGFACE_IMG }}-${{ github.sha }}
+          path: ./tmp
+
+      - name: Load docker images
+        uses: ./.github/actions/load-docker-images
+        with:
+          directory: ./tmp
+
+      - name: Install Poetry and version plugin
+        run: ./test/scripts/gh-actions/setup-poetry.sh
+
+      - name: Install KServe
+        run: |
+          ./test/scripts/gh-actions/setup-kserve.sh
+
+          kubectl get pods -n kserve
+          kubectl describe pods -n kserve
+
+      - name: Run E2E tests
+        timeout-minutes: 30
+        run: |
+          ./test/scripts/gh-actions/run-e2e-tests.sh "llm" "2"
+
+      - name: Check system status
+        if: always()
+        run: |
+          ./test/scripts/gh-actions/status-check.sh

.github/workflows/go.yml

@@ -29,10 +29,6 @@ jobs:
         run: |
           go get -v -t -d ./...
 
-      - name: Go lint
-        run: |
-          make fmt
-
       - name: Test
         id: test
         run: |
@@ -57,4 +53,4 @@ jobs:
           filename: coverage.json
           label: coverage
           message: ${{ steps.test.outputs.coverage }}
-          color: green
+          color: green

.github/workflows/golangci-lint.yml

@@ -0,0 +1,28 @@
+name: golangci-lint
+on:
+  push:
+    branches:
+      - master
+      - main
+  pull_request:
+
+permissions:
+  contents: read
+  pull-requests: read
+
+jobs:
+  golangci:
+    name: lint
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-go@v5
+        with:
+          go-version: '1.21'
+          cache: false
+      - name: golangci-lint
+        uses: golangci/golangci-lint-action@v4
+        with:
+          version: v1.56
+          args: --out-format=line-number
+