Merge pull request #255 from spolti/sync

Sync community with ODH

.github/workflows/codeql.yml

@@ -0,0 +1,82 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: [ "main" ]
+  schedule:
+    - cron: '00 8 * * *'
+
+jobs:
+  analyze:
+    name: Analyze
+    # Runner size impacts CodeQL analysis time. To learn more, please see:
+    #   - https://gh.io/recommended-hardware-resources-for-running-codeql
+    #   - https://gh.io/supported-runners-and-hardware-resources
+    #   - https://gh.io/using-larger-runners
+    # Consider using larger runners for possible analysis time improvements.
+    runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }}
+    timeout-minutes: ${{ (matrix.language == 'swift' && 120) || 360 }}
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: [ 'go', 'python' ]
+        # CodeQL supports [ 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'swift' ]
+        # Use only 'java-kotlin' to analyze code written in Java, Kotlin or both
+        # Use only 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both
+        # Learn more about CodeQL language support at https://aka.ms/codeql-docs/language-support
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v3
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v2
+      with:
+        languages: ${{ matrix.language }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+
+        # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+        # queries: security-extended,security-and-quality
+
+
+    # Autobuild attempts to build any compiled languages (C/C++, C#, Go, Java, or Swift).
+    # If this step fails, then you should remove it and run the build manually (see below)
+    - name: Autobuild
+      uses: github/codeql-action/autobuild@v2
+
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+
+    #   If the Autobuild fails above, remove it and uncomment the following three lines.
+    #   modify them (or add more) to build your code if your project, please refer to the EXAMPLE below for guidance.
+
+    # - run: |
+    #     echo "Run, Build Application using script"
+    #     ./location_of_script_within_repo/buildscript.sh
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v2
+      with:
+        category: "/language:${{matrix.language}}"

.github/workflows/fvt.yml → .github/workflows/fvt-base.yml

@@ -1,4 +1,4 @@
-name: FVT
+name: FVT Base
 
 on:
   workflow_dispatch:
@@ -94,6 +94,7 @@ jobs:
 
       - name: Install ModelMesh Serving
         run: |
+          export NAMESPACE_SCOPE_MODE=${{ inputs.namespace-scope-mode }}
           kubectl create ns modelmesh-serving
           ./scripts/install.sh --namespace modelmesh-serving --fvt --dev-mode-logging
 
@@ -121,13 +122,15 @@ jobs:
         run: |
           eval $(minikube -p minikube docker-env)
           docker images
+          kubectl get svc
           kubectl get pods
-          kubectl get clusterservingruntimes
+          kubectl get clusterservingruntimes 2> /dev/null || :
+          kubectl get servingruntimes 2> /dev/null || :
 
       - name: Run FVTs
         run: |
           go install github.com/onsi/ginkgo/v2/ginkgo
           export PATH=/root/go/bin/:$PATH
           export NAMESPACE=modelmesh-serving
-          export NAMESPACESCOPEMODE=false
+          export NAMESPACESCOPEMODE=${{ inputs.namespace-scope-mode }}
           make fvt

.github/workflows/fvt-cs.yml

@@ -0,0 +1,22 @@
+name: FVT Cluster Scope
+
+on:
+  workflow_dispatch:
+  pull_request:
+    branches:
+      - main
+      - 'release-[0-9].[0-9]+'
+    paths:
+      - '**'
+      - '!.github/**'
+      - '!.tekton/**'
+      - '!**.md'
+      - '!docs/**'
+      - '.github/workflows/fvt*.yml'
+
+jobs:
+  fvt-cluster-scope:
+    uses: ./.github/workflows/fvt-base.yml
+    with:
+      namespace-scope-mode: false
+    secrets: inherit

.github/workflows/fvt-ns.yml

@@ -0,0 +1,22 @@
+name: FVT Namespace Scope
+
+on:
+  workflow_dispatch:
+  pull_request:
+    branches:
+      - main
+      - 'release-[0-9].[0-9]+'
+    paths:
+      - '**'
+      - '!.github/**'
+      - '!.tekton/**'
+      - '!**.md'
+      - '!docs/**'
+      - '.github/workflows/fvt*.yml'
+
+jobs:
+  fvt-namespace-scope:
+    uses: ./.github/workflows/fvt-base.yml
+    with:
+      namespace-scope-mode: true
+    secrets: inherit

.gitignore

@@ -1,6 +1,8 @@
 # general
 .env
 .DS_Store
+.run/
+temp/
 
 public/
 target/
@@ -31,7 +33,7 @@ bin
 .vscode
 *~
 
-# Modelmesh development related artifacts
+# ModelMesh development related artifacts
 devbuild
 .develop_image_name
 .dev/

Dockerfile.develop

@@ -36,18 +36,20 @@ ENV HOME=/root
 WORKDIR /workspace
 
 # Install build and dev tools
+# NOTE: Require python38 to install pre-commit
 RUN --mount=type=cache,target=/root/.cache/dnf:rw \
     dnf install --setopt=cachedir=/root/.cache/dnf -y --nodocs \
-       python3 \
-       python3-pip \
        nodejs \
        jq \
+       python38 \
+    && ln -sf /usr/bin/python3 /usr/bin/python \
+    && ln -sf /usr/bin/pip3 /usr/bin/pip \
     && true
 
 # Install pre-commit
 ENV PIP_CACHE_DIR=/root/.cache/pip
 RUN --mount=type=cache,target=/root/.cache/pip \
-    pip3 install pre-commit
+    pip install pre-commit
 
 # First download and extract older dist of kubebuilder which includes required etcd, kube-apiserver and kubectl binaries
 # Then download and overwrite kubebuilder binary with desired/latest version

Dockerfile.develop.ci

@@ -36,17 +36,20 @@ ENV HOME=/go
 WORKDIR /go/src/github.com/opendatahub-io/modelmesh-serving/
 
 # Install build and dev tools
-RUN --mount=type=cache,target=${HOME}/.cache/dnf:rw \
-    dnf install --setopt=cachedir=${HOME}/.cache/dnf -y --nodocs \
-       python3 \
-       python3-pip \
+# NOTE: Require python38 to install pre-commit
+RUN --mount=type=cache,target=/root/.cache/dnf:rw \
+    dnf install --setopt=cachedir=/root/.cache/dnf -y --nodocs \
        nodejs \
-       jq
+       jq \
+       python38 \
+    && ln -sf /usr/bin/python3 /usr/bin/python \
+    && ln -sf /usr/bin/pip3 /usr/bin/pip \
+    && true
 
 # Install pre-commit
-ENV PIP_CACHE_DIR=${HOME}/.cache/pip
-RUN --mount=type=cache,target=${HOME}/.cache/pip \
-    pip3 install pre-commit
+ENV PIP_CACHE_DIR=/root/.cache/pip
+RUN --mount=type=cache,target=/root/.cache/pip \
+    pip install pre-commit
 
 # First download and extract older dist of kubebuilder which includes required etcd, kube-apiserver and kubectl binaries
 # Then download and overwrite kubebuilder binary with desired/latest version

controllers/hpa/hpa_reconciler.go

@@ -59,8 +59,11 @@ func getHPAMetrics(metadata metav1.ObjectMeta) []hpav2.MetricSpec {
 	resourceName := corev1.ResourceCPU
 
 	if value, ok := annotations[constants.TargetUtilizationPercentage]; ok {
-		utilizationInt, _ := strconv.Atoi(value)
-		utilization = int32(utilizationInt)
+		if valueInt, err := strconv.ParseInt(value, 10, 32); err != nil {
+			log.Error(err, "Could not parse TargetUtilizationPercentage", "value", value)
+		} else {
+			utilization = int32(valueInt)
+		}
 	}
 
 	if value, ok := annotations[constants.AutoscalerMetrics]; ok {
@@ -90,13 +93,19 @@ func createHPA(runtimeMeta metav1.ObjectMeta, mmDeploymentName string, mmNamespa
 	annotations := runtimeMeta.Annotations
 
 	if value, ok := annotations[mmcontstant.MinScaleAnnotationKey]; ok {
-		minReplicasInt, _ := strconv.Atoi(value)
-		minReplicas = int32(minReplicasInt)
-
+		if valueInt, err := strconv.ParseInt(value, 10, 32); err != nil {
+			log.Error(err, "Could not parse MinScaleAnnotationKey", "value", value)
+		} else {
+			minReplicas = int32(valueInt)
+		}
 	}
+
 	if value, ok := annotations[mmcontstant.MaxScaleAnnotationKey]; ok {
-		maxReplicasInt, _ := strconv.Atoi(value)
-		maxReplicas = int32(maxReplicasInt)
+		if valueInt, err := strconv.ParseInt(value, 10, 32); err != nil {
+			log.Error(err, "Could not parse MaxScaleAnnotationKey", "value", value)
+		} else {
+			maxReplicas = int32(valueInt)
+		}
 	}
 
 	if maxReplicas < minReplicas {

controllers/modelmesh/modelmesh.go

@@ -265,29 +265,30 @@ func (m *Deployment) addMMEnvVars(deployment *appsv1.Deployment) error {
 	}
 
 	if m.EnableAccessLogging {
-		// See https://github.com/kserve/modelmesh/blob/v0.11.0/src/main/java/com/ibm/watson/modelmesh/ModelMeshEnvVars.java#L55
+		// See https://github.com/kserve/modelmesh/blob/v0.11.1/src/main/java/com/ibm/watson/modelmesh/ModelMeshEnvVars.java#L55
 		if err := setEnvironmentVar(ModelMeshContainerName, "MM_LOG_EACH_INVOKE", "true", deployment); err != nil {
 			return err
 		}
 	}
 
 	if m.GrpcMaxMessageSize > 0 {
-		// See https://github.com/kserve/modelmesh/blob/v0.11.0/src/main/java/com/ibm/watson/modelmesh/ModelMeshEnvVars.java#L38
+		// See https://github.com/kserve/modelmesh/blob/v0.11.1/src/main/java/com/ibm/watson/modelmesh/ModelMeshEnvVars.java#L38
 		if err := setEnvironmentVar(ModelMeshContainerName, "MM_SVC_GRPC_MAX_MSG_SIZE", strconv.Itoa(m.GrpcMaxMessageSize), deployment); err != nil {
 			return err
 		}
 	}
 
-	// See https://github.com/kserve/modelmesh/blob/v0.11.0/src/main/java/com/ibm/watson/modelmesh/ModelMeshEnvVars.java#L31
+	// See https://github.com/kserve/modelmesh/blob/v0.11.1/src/main/java/com/ibm/watson/modelmesh/ModelMeshEnvVars.java#L31
 	if err := setEnvironmentVar(ModelMeshContainerName, "MM_KVSTORE_PREFIX", ModelMeshEtcdPrefix, deployment); err != nil {
 		return err
 	}
-	// See https://github.com/kserve/modelmesh/blob/v0.11.0/src/main/java/com/ibm/watson/modelmesh/ModelMeshEnvVars.java#L68
+	// See https://github.com/kserve/modelmesh/blob/v0.11.1/src/main/java/com/ibm/watson/modelmesh/ModelMeshEnvVars.java#L68
 	if err := setEnvironmentVar(ModelMeshContainerName, "MM_DEFAULT_VMODEL_OWNER", m.DefaultVModelOwner, deployment); err != nil {
 		return err
 	}
 
 	if len(m.PayloadProcessors) > 0 {
+		// See https://github.com/kserve/modelmesh/blob/v0.11.1/src/main/java/com/ibm/watson/modelmesh/ModelMeshEnvVars.java#L26
 		if err := setEnvironmentVar(ModelMeshContainerName, "MM_PAYLOAD_PROCESSORS", m.PayloadProcessors, deployment); err != nil {
 			return err
 		}

docs/model-formats/openvino-ir.md

@@ -2,13 +2,13 @@
 
 ## Format
 
-Full documentation on OpenVINO IR format can be found [here](https://docs.openvino.ai/2022.1/openvino_docs_MO_DG_IR_and_opsets.html#intermediate-representation-used-in-openvino).
+Full documentation on OpenVINO IR format can be found [here](https://docs.openvino.ai/2022.3/openvino_docs_MO_DG_IR_and_opsets.html#intermediate-representation-used-in-openvino).
 
 OpenVINO™ toolkit introduces its own format of graph representation and its own operation set. A graph is represented with two files: an XML file and a binary file. This representation is commonly referred to as the Intermediate Representation or IR.
 
-An example of a small IR XML file can be found in the same [link above](https://docs.openvino.ai/2022.1/openvino_docs_MO_DG_IR_and_opsets.html#intermediate-representation-used-in-openvino). The XML file doesn’t have big constant values, like convolution weights. Instead, it refers to a part of the accompanying binary file that stores such values in a binary format.
+An example of a small IR XML file can be found in the same [link above](https://docs.openvino.ai/2022.3/openvino_docs_MO_DG_IR_and_opsets.html#intermediate-representation-used-in-openvino). The XML file doesn’t have big constant values, like convolution weights. Instead, it refers to a part of the accompanying binary file that stores such values in a binary format.
 
-Models trained in other formats (Caffe, TensorFlow, MXNet, PaddlePaddle and ONNX) can be converted to OpenVINO IR format. To do so, use OpenVINO’s [Model Optimizer](https://docs.openvino.ai/2022.1/openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html).
+Models trained in other formats (Caffe, TensorFlow, MXNet, PaddlePaddle and ONNX) can be converted to OpenVINO IR format. To do so, use OpenVINO’s [Model Optimizer](https://docs.openvino.ai/2022.3/openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html).
 
 ## Configuration
 
@@ -20,7 +20,7 @@ Here is an example of client code:
 input_tensorname = 'input'
 request.inputs[input_tensorname].CopyFrom(make_tensor_proto(img, shape=(1, 3, 224, 224)))
 
-.....
+...
 
 output_tensorname = 'resnet_v1_50/predictions/Reshape_1'
 predictions = make_ndarray(result.outputs[output_tensorname])
@@ -46,21 +46,22 @@ More details on model configuration can be found [here](https://docs.openvino.ai
 
 The OpenVINO models need to be placed and mounted in a particular directory structure:
 
-```
+```shell
 tree models/
+
 models/
 ├── model1
-│   ├── 1
-│   │   ├── ir_model.bin
-│   │   └── ir_model.xml
-│   └── 2
-│       ├── ir_model.bin
-│       └── ir_model.xml
+│   ├── 1
+│   │   ├── ir_model.bin
+│   │   └── ir_model.xml
+│   └── 2
+│       ├── ir_model.bin
+│       └── ir_model.xml
 └── model2
-│   └── 1
-│       ├── ir_model.bin
-│       ├── ir_model.xml
-│       └── mapping_config.json
+│   └── 1
+│       ├── ir_model.bin
+│       ├── ir_model.xml
+│       └── mapping_config.json
 └── model3
     └── 1
         └── model.onnx

docs/predictors/run-inference.md

@@ -190,7 +190,7 @@ This would give a response similar to the following:
     {
       "name": "predict",
       "datatype": "FP32",
-      "shape": [1],
+      "shape": [1, 1],
       "data": [8]
     }
   ]