Merge pull request #976 from mholder6/20251118_sync_upstream

20251118 sync upstream

Author: mholder6

.flake8

@@ -15,6 +15,7 @@ exclude =
   python/kserve/test/__init__.py,
   python/kserve/test/test_knative*.py,
   python/kserve/kserve/protocol/grpc/grpc_predict_v2*.py
+  python/kserve/build/**/*.py
   python/*_pb2.py
   docs/**/*.py
   python/kserve/kserve/protocol/rest/openai/types/openapi.py

.github/workflows/e2e-test.yml

@@ -415,7 +415,12 @@ jobs:
       - name: Run E2E tests
         timeout-minutes: 30
         run: |
-          ./test/scripts/gh-actions/run-e2e-tests.sh "transformer or mms or collocation or explainer" "6"
+          ./test/scripts/gh-actions/run-e2e-tests.sh "transformer or mms or collocation" "6"
+
+      - name: Run E2E tests - explainer
+        timeout-minutes: 30
+        run: |
+          ./test/scripts/gh-actions/run-e2e-tests.sh "explainer" "1"
 
       - name: Check system status
         if: always()
@@ -583,6 +588,11 @@ jobs:
         run: |
           ./test/scripts/gh-actions/run-e2e-tests.sh "path_based_routing" "6"
 
+      - name: Run E2E tests with path-based routing - Explainer
+        timeout-minutes: 30
+        run: |
+          ./test/scripts/gh-actions/run-e2e-tests.sh "explainer" "1"
+
       - name: Check system status
         if: always()
         run: |

.github/workflows/python-test.yml

@@ -74,6 +74,11 @@ jobs:
           cd python
           source kserve/.venv/bin/activate
           pytest --cov=kserve ./kserve
+      - name: Test kserve Storage
+        run: |
+          cd python
+          source kserve/.venv/bin/activate
+          pytest --cov=storage ./storage
 
       # ----------------------------------------Kserve Numpy 1.x Unit Tests--------------------------------------------
       - name: Setup kserve numpy 1-x directory

.github/workflows/scheduled-image-scan.yml

@@ -14,6 +14,7 @@ jobs:
     name: scan images
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
         image:
           [
@@ -53,15 +54,16 @@ jobs:
 
       - name: Upload sarif file to Github Code Scanning
         if: always()
-        continue-on-error: true #avoid fail the pipeline if the SARIF upload fails.
         uses: github/codeql-action/upload-sarif@v3
         with:
           sarif_file: application/${{ matrix.image.name }}/docker.snyk.sarif
+          category: ${{ matrix.image.name }}
 
   predictor-image-scan:
     name: scan predictor images
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
         image:
           [
@@ -104,11 +106,13 @@ jobs:
         uses: github/codeql-action/upload-sarif@v3
         with:
           sarif_file: application/${{ matrix.image.name }}/docker.snyk.sarif
+          category: ${{ matrix.image.name }}
 
   explainer-image-scan:
     name: scan explainer images
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
         image: [{ name: art-explainer, file: python/artexplainer.Dockerfile }]
 
@@ -143,3 +147,4 @@ jobs:
         uses: github/codeql-action/upload-sarif@v3
         with:
           sarif_file: application/${{ matrix.image.name }}/docker.snyk.sarif
+          category: ${{ matrix.image.name }}

charts/llmisvc-crd/templates/serving.kserve.io_llminferenceserviceconfigs.yaml

@@ -46,24 +46,7 @@ spec:
                     lora:
                       properties:
                         adapters:
-                          items:
-                            properties:
-                              framework:
-                                type: string
-                              memory:
-                                anyOf:
-                                  - type: integer
-                                  - type: string
-                                pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
-                                x-kubernetes-int-or-string: true
-                              storageUri:
-                                type: string
-                            required:
-                              - framework
-                              - memory
-                              - storageUri
-                            type: object
-                          type: array
+                          x-kubernetes-preserve-unknown-fields: true
                       type: object
                     name:
                       type: string

charts/llmisvc-crd/templates/serving.kserve.io_llminferenceservices.yaml

@@ -65,24 +65,7 @@ spec:
                   lora:
                     properties:
                       adapters:
-                        items:
-                          properties:
-                            framework:
-                              type: string
-                            memory:
-                              anyOf:
-                              - type: integer
-                              - type: string
-                              pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
-                              x-kubernetes-int-or-string: true
-                            storageUri:
-                              type: string
-                          required:
-                          - framework
-                          - memory
-                          - storageUri
-                          type: object
-                        type: array
+                        x-kubernetes-preserve-unknown-fields: true
                     type: object
                   name:
                     type: string

charts/llmisvc-resources/templates/config-llm-decode-template.yaml

@@ -5,7 +5,7 @@ metadata:
 spec:
   template:
     containers:
-      - image: ghcr.io/llm-d/llm-d:v0.2.0
+      - image: ghcr.io/llm-d/llm-d-dev:v0.2.2
         imagePullPolicy: IfNotPresent
         name: main
         ports:
@@ -14,6 +14,7 @@ spec:
         command:
           - vllm
           - serve
+          - /mnt/models
         args:
           - --served-model-name
           - "{{ .Spec.Model.Name }}"
@@ -34,9 +35,13 @@ spec:
             value: /models
         securityContext:
           allowPrivilegeEscalation: false
+          readOnlyRootFilesystem: false
+          runAsNonRoot: true
           capabilities:
             drop:
-              - MKNOD
+              - ALL
+          seccompProfile:
+            type: RuntimeDefault
         terminationMessagePath: /dev/termination-log
         terminationMessagePolicy: FallbackToLogsOnError
         livenessProbe:
@@ -76,7 +81,13 @@ spec:
           - containerPort: 8000
             protocol: TCP
         resources: { }
-        securityContext: { }
+        securityContext:
+          allowPrivilegeEscalation: false
+          readOnlyRootFilesystem: false
+          runAsNonRoot: true
+          capabilities:
+            drop:
+              - ALL
         terminationMessagePath: /dev/termination-log
         terminationMessagePolicy: FallbackToLogsOnError
         livenessProbe:
@@ -100,6 +111,7 @@ spec:
         args:
           - "--port=8000"
           - "--vllm-port=8001"
+          - "--connector=nixlv2"
           - "--secure-proxy=true"
           - "--cert-path=/etc/ssl/certs"
           - "--decoder-use-tls=true"
@@ -128,4 +140,4 @@ spec:
         name: model-cache
       - name: tls-certs
         secret:
-          secretName: "{{ ChildName .ObjectMeta.Name `-kserve-self-signed-certs` }}"
+          secretName: "{{ ChildName .ObjectMeta.Name `-kserve-self-signed-certs` }}"