[pull] master from kserve:master

.github/workflows/python-test.yml

@@ -175,35 +175,32 @@ jobs:
           pytest --cov=lgbserver ./lgbserver
 
       # ----------------------------------------Paddle Server Unit Tests------------------------------------------------
-      # load cached paddle venv if cache exists and paddle test should not run if python version is 3.11
+      # load cached paddle venv if cache exists
       - name: Load cached paddle venv
-        if: ${{ !startsWith(steps.setup-python.outputs.python-version, '3.11') }}
         id: cached-paddle-dependencies
         uses: actions/cache@v3
         with:
           path: python/paddleserver/.venv
           key: paddle-venv-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/kserve/poetry.lock', '**/paddleserver/poetry.lock') }}
         # install paddle server dependencies if cache does not exist
       - name: Install paddle dependencies
-        if: ${{ steps.cached-paddle-dependencies.outputs.cache-hit != 'true' && !startsWith(steps.setup-python.outputs.python-version, '3.11') }}
+        if: steps.cached-paddle-dependencies.outputs.cache-hit != 'true'
         run: |
           echo "python version ${{ steps.setup-python.outputs.python-version }}"
           cd python/paddleserver
           make install_dependencies
       - name: Install paddleserver
-        if: ${{ !startsWith(steps.setup-python.outputs.python-version, '3.11') }}
         run: |
           cd python/paddleserver
           make dev_install
       - name: Test paddleserver
-        if: ${{ !startsWith(steps.setup-python.outputs.python-version, '3.11') }}
         run: |
           cd python
           source paddleserver/.venv/bin/activate
           pytest --cov=paddleserver ./paddleserver
 
       # ----------------------------------------Alibi Explainer Unit Tests------------------------------------------------
-      # load cached alibi venv if cache exists and alibi test should not run if python version is 3.11
+      # load cached alibi venv if cache exists
       - name: Load cached alibi venv
         id: cached-alibi-dependencies
         uses: actions/cache@v3

qpext/README.md

@@ -20,7 +20,7 @@ see also: [KServe Issue #2645](https://github.com/kserve/kserve/issues/2465),
 Save this file as qpext_image_patch.yaml, update the tag if needed.
 ```yaml
 data:
-  queueSidecarImage: kserve/qpext:latest
+  queue-sidecar-image: kserve/qpext:latest
 ```
 
 Run the following command to patch the deployment config in the appropriate knative namespace.
@@ -158,7 +158,7 @@ docker push {some_docker_repo}/qpext:latest
 (2) Save this file as qpext_image_patch.yaml, update the tag if needed.
 ```yaml
 data:
-  queueSidecarImage: kserve/qpext:latest
+  queue-sidecar-image: kserve/qpext:latest
 ```
 
 (3) Run the following command to patch the deployment config in the appropriate knative namespace.
@@ -184,7 +184,7 @@ and annotations on the pod, check the Pod output.
 kubectl get pod {name_of_pod} -oyaml
 ```
 
-To check that the metrics are aggregated, use the KServe [Getting Started](https://kserve.github.io/website/0.9/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) 
+To check that the metrics are aggregated, use the KServe [Getting Started](https://kserve.github.io/website/latest/get_started/first_isvc/#4-determine-the-ingress-ip-and-ports) 
 documentation as a guide to send a request to the pod. Next, send a request to the metrics endpoint. 
 
 For example, port-forward the pod prometheus aggregate metrics port to localhost. 
@@ -193,5 +193,5 @@ kubectl port-forward pods/{pod_name} 9088:9088
 ```
 Next, cURL the port to see the metrics output.
 ```shell
-curl localhost:9088
+curl localhost:9088/metrics
 ```