[pull] master from kserve:master

.github/actions/free-up-disk-space/action.yml

@@ -1,5 +1,5 @@
 name: 'Free-up disk space action'
-description: 'Removes non-essential tools, libraries and cached files from GitHub action runner node'
+description: 'Removes non-essential tools, libraries and cached files from GitHub action runner node and changes the docker data directory to /mnt/docker'
 
 runs:
   using: "composite"
@@ -8,7 +8,7 @@ runs:
       shell: bash
       run: |
         echo "Disk usage before cleanup:"
-        df -h
+        df -hT
 
         # remove non-essential tools and libraries, see:
         # https://github.com/actions/runner-images/issues/2840#issuecomment-790492173
@@ -23,12 +23,30 @@ runs:
         sudo rm -rf /usr/share/swift
 
         echo "Disk usage after cleanup:"
-        df -h
+        df -hT
 
     - name: Prune docker images
       shell: bash
       run: |
         echo "Pruning docker images"
         docker image prune -a -f
         docker system df
-        df -h
+        df -hT
+
+    - name: Move docker data directory
+      shell: bash
+      run: |
+        echo "Stopping docker service ..."
+        sudo systemctl stop docker
+        DOCKER_DEFAULT_ROOT_DIR=/var/lib/docker
+        DOCKER_ROOT_DIR=/mnt/docker
+        echo "Moving ${DOCKER_DEFAULT_ROOT_DIR} -> ${DOCKER_ROOT_DIR}"
+        sudo mv ${DOCKER_DEFAULT_ROOT_DIR} ${DOCKER_ROOT_DIR}
+        echo "Creating symlink ${DOCKER_DEFAULT_ROOT_DIR} -> ${DOCKER_ROOT_DIR}"
+        sudo ln -s ${DOCKER_ROOT_DIR} ${DOCKER_DEFAULT_ROOT_DIR}
+        echo "$(sudo ls -l ${DOCKER_DEFAULT_ROOT_DIR})"
+        echo "Starting docker service ..."
+        sudo systemctl daemon-reload
+        sudo systemctl start docker
+        echo "Docker service status:"
+        sudo systemctl --no-pager -l -o short status docker

.github/workflows/huggingface-docker-publish.yml

@@ -0,0 +1,87 @@
+name: Huggingface Docker Publisher
+
+on:
+  push:
+    # Publish `master` as Docker `latest` image.
+    branches:
+      - master
+
+  # Run tests for any PRs.
+  pull_request:
+
+env:
+  IMAGE_NAME: huggingfaceserver 
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  # Run tests.
+  # See also https://docs.docker.com/docker-hub/builds/automated-testing/
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout source
+        uses: actions/checkout@v2
+
+      - name: Free-up disk space
+        uses: ./.github/actions/free-up-disk-space
+
+      - 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 huggingface_server.Dockerfile
+          fi
+
+  # Push image to GitHub Packages.
+  # See also https://docs.docker.com/docker-hub/builds/
+  push:
+    # Ensure test job passes before pushing image.
+    needs: test
+
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push'
+
+    steps:
+      - name: Checkout source
+        uses: actions/checkout@v2
+
+      - name: Free-up disk space
+        uses: ./.github/actions/free-up-disk-space
+
+      - name: Build image
+        run: |
+          cd python
+          docker buildx build . --file huggingface_server.Dockerfile --tag $IMAGE_NAME
+
+      - name: Log into registry
+        run: docker login -u ${{ secrets.DOCKER_USER }} -p ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Push image
+        run: |
+          IMAGE_ID=kserve/$IMAGE_NAME
+
+          # Change all uppercase to lowercase
+          IMAGE_ID=$(echo $IMAGE_ID | tr '[A-Z]' '[a-z]')
+
+          # Strip git ref prefix from version
+          VERSION=$(echo "${{ github.ref }}" | sed -e 's,.*/\(.*\),\1,')
+
+          # Strip "v" prefix from tag name
+          # [[ "${{ github.ref }}" == "refs/tags/"* ]] && VERSION=$(echo $VERSION | sed -e 's/^v//')
+
+          # Use Docker `latest` tag convention
+          [ "$VERSION" == "master" ] && VERSION=latest
+
+          echo IMAGE_ID=$IMAGE_ID
+          echo VERSION=$VERSION
+
+          docker tag $IMAGE_NAME $IMAGE_ID:$VERSION
+          docker push $IMAGE_ID:$VERSION
+

.github/workflows/python-test.yml

@@ -29,14 +29,19 @@ jobs:
         uses: py-actions/flake8@v1
         with:
           max-line-length: "120"
-          exclude: "docs/samples/v1beta1/onnx/assets/*.py,python/kserve/test/test_v1*.py,python/kserve/kserve/__init__.py,python/kserve/test/test_knative*.py,python/kserve/kserve/protocol/grpc/grpc_predict_v2*.py"
+          exclude: "docs/samples/v1beta1/onnx/assets/*.py,python/kserve/kserve/*.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"
   build:
     runs-on: ubuntu-latest
     strategy:
       matrix:
         python-version: ["3.8", "3.9", "3.10", "3.11"]
     steps:
-      - uses: actions/checkout@v2
+      - name: Checkout source
+        uses: actions/checkout@v2
+
+      - name: Free-up disk space
+        uses: ./.github/actions/free-up-disk-space
+
       - name: Set up Python ${{ matrix.python-version }}
         id: setup-python
         uses: actions/setup-python@v4
@@ -46,12 +51,19 @@ jobs:
       - name: Install Poetry and version plugin
         run: ./test/scripts/gh-actions/setup-poetry.sh
 
+      - name: Configure Poetry cache
+        run: |
+          sudo mkdir -p /mnt/poetry
+          # change permission so that poetry can install without sudo
+          sudo chown -R $USER /mnt/poetry
+          poetry config cache-dir /mnt/poetry
+
       # load poetry cache if cache exists
       - name: Load poetry cache
         id: cached-poetry-dependencies
         uses: actions/cache@v3
         with:
-          path: ~/.cache/pypoetry
+          path: /mnt/poetry
           key: poetry-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}
 
       # ----------------------------------------Kserve Unit Tests--------------------------------------------------------
@@ -221,3 +233,41 @@ jobs:
           cd python
           source alibiexplainer/.venv/bin/activate
           pytest --cov=alibiexplainer ./alibiexplainer
+
+      # ----------------------------------------Huggingface Server Unit Tests------------------------------------------------
+      # load cached huggingface venv if cache exists
+      - name: Load cached huggingface venv
+        if: ${{ !startsWith(steps.setup-python.outputs.python-version, '3.8') }}
+        id: huggingface-dependencies
+        uses: actions/cache@v3
+        with:
+          path: /mnt/python/huggingfaceserver-venv
+          key: huggingface-venv-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/kserve/poetry.lock', '**/huggingfaceserver/poetry.lock') }}
+        # install huggingface server dependencies if cache does not exist
+      - name: Configure poetry for huggingface server
+        if: ${{ !startsWith(steps.setup-python.outputs.python-version, '3.8') }}
+        run: |
+          poetry config virtualenvs.path /mnt/python/huggingfaceserver-venv
+          poetry config virtualenvs.in-project false
+      - name: Install huggingface dependencies
+        if: ${{ steps.cached-huggingface-dependencies.outputs.cache-hit != 'true' && !startsWith(steps.setup-python.outputs.python-version, '3.8') }}
+        run: |
+          sudo mkdir -p /mnt/python/huggingfaceserver-venv
+          # change permission so that poetry can install without sudo
+          sudo chown -R $USER /mnt/python/huggingfaceserver-venv
+          cd python/huggingfaceserver
+          make install_dependencies
+      - name: Install huggingface server
+        if: ${{ !startsWith(steps.setup-python.outputs.python-version, '3.8') }}
+        run: |
+          cd python/huggingfaceserver
+          make dev_install
+      - name: Test huggingfaceserver
+        if: ${{ !startsWith(steps.setup-python.outputs.python-version, '3.8') }}
+        run: |
+          cd python/huggingfaceserver
+          poetry run -- pytest --cov=huggingfaceserver
+
+      - name: Free space after tests
+        run: |
+          df -hT

README.md

@@ -5,7 +5,7 @@
 [![OpenSSF Best Practices](https://bestpractices.coreinfrastructure.org/projects/6643/badge)](https://bestpractices.coreinfrastructure.org/projects/6643)
 [![Releases](https://img.shields.io/github/release-pre/kserve/kserve.svg?sort=semver)](https://github.com/kserve/kserve/releases)
 [![LICENSE](https://img.shields.io/github/license/kserve/kserve.svg)](https://github.com/kserve/kserve/blob/master/LICENSE)
-[![Slack Status](https://img.shields.io/badge/slack-join_chat-white.svg?logo=slack&style=social)](https://kubeflow.slack.com/archives/CH6E58LNP)
+[![Slack Status](https://img.shields.io/badge/slack-join_chat-white.svg?logo=slack&style=social)](https://github.com/kserve/community/blob/main/README.md#questions-and-issues)
 
 KServe provides a Kubernetes [Custom Resource Definition](https://kubernetes.io/docs/concepts/extend-kubernetes/api-extension/custom-resources/) for serving machine learning (ML) models on arbitrary frameworks. It aims to solve production model serving use cases by providing performant, high abstraction interfaces for common ML frameworks like Tensorflow, XGBoost, ScikitLearn, PyTorch, and ONNX.
 

charts/kserve-resources/templates/clusterservingruntimes.yaml

@@ -344,3 +344,32 @@ spec:
         limits:
           cpu: "1"
           memory: 2Gi
+---
+apiVersion: serving.kserve.io/v1alpha1
+kind: ClusterServingRuntime
+metadata:
+  name: kserve-huggingfaceserver
+spec:
+  annotations:
+    prometheus.kserve.io/port: '8080'
+    prometheus.kserve.io/path: "/metrics"
+  supportedModelFormats:
+    - name: huggingface
+      version: "1"
+      autoSelect: true
+      priority: 1
+  protocolVersions:
+    - v2
+  containers:
+    - name: kserve-container
+      image: "{{ .Values.kserve.servingruntime.huggingfaceserver.image }}:{{ .Values.kserve.servingruntime.huggingfaceserver.tag }}"
+      args:
+        - --model_id={{.Name}}
+        - --model_dir=/mnt/models
+      resources:
+        requests:
+          cpu: "1"
+          memory: 2Gi
+        limits:
+          cpu: "1"
+          memory: 2Gi

charts/kserve-resources/values.yaml

@@ -101,6 +101,9 @@ kserve:
     xgbserver:
       image: kserve/xgbserver
       tag: *defaultVersion
+    huggingfaceserver:
+      image: kserve/huggingfaceserver
+      tag: *defaultVersion
     tritonserver:
       image: nvcr.io/nvidia/tritonserver
       tag: 23.05-py3

config/configmap/inferenceservice.yaml

@@ -132,6 +132,7 @@ data:
               "s3Region": "",
               "s3VerifySSL": "",
               "s3UseVirtualBucket": "",
+              "s3UseAccelerate": "",
               "s3UseAnonymousCredential": "",
               "s3CABundle": ""
           }
@@ -186,6 +187,9 @@ data:
 
               # s3UseVirtualBucket configures whether it is a virtual bucket or not.
               "s3UseVirtualBucket": "",
+
+              # s3UseAccelerate configures whether to use transfer acceleration.
+              "s3UseAccelerate": "",
 
               # s3UseAnonymousCredential configures whether to use anonymous credentials to download the model or not.
               "s3UseAnonymousCredential": "",
@@ -489,6 +493,7 @@ data:
            "s3Region": "",
            "s3VerifySSL": "",
            "s3UseVirtualBucket": "",
+           "s3UseAccelerate": "",
            "s3UseAnonymousCredential": "",
            "s3CABundle": ""
        }

config/crd/patches/protocol.yaml

@@ -10,6 +10,10 @@
   path: /spec/validation/openAPIV3Schema/properties/spec/properties/predictor/properties/onnx/properties/ports/items/required/1
   value: protocol
 
+- op: add
+  path: /spec/validation/openAPIV3Schema/properties/spec/properties/predictor/properties/huggingface/properties/ports/items/required/1
+  value: protocol
+
 - op: add
   path: /spec/validation/openAPIV3Schema/properties/spec/properties/predictor/properties/sklearn/properties/ports/items/required/1
   value: protocol