Add bigdl llm cpu image build (#9047)

* modify Dockerfile

* add README.md

* add README.md

* Modify Dockerfile

* Add bigdl inference cpu image build

* Add bigdl llm cpu image build

* Add bigdl llm cpu image build

* Add bigdl llm cpu image build

.github/workflows/manually_build.yml

@@ -10,6 +10,7 @@ on:
         type: choice
         options:
         - all
+        - bigdl-llm-cpu
         - bigdl-ppml-gramine-base
         - bigdl-ppml-trusted-bigdl-llm-gramine-base
         - bigdl-ppml-trusted-bigdl-llm-gramine-ref
@@ -54,6 +55,34 @@ permissions:
   packages: write
 
 jobs:
+  bigdl-llm-cpu:
+    if: ${{ github.event.inputs.artifact == 'bigdl-llm-cpu' || github.event.inputs.artifact == 'all' }}
+    runs-on: [self-hosted, Shire]
+    steps:
+    - uses: actions/checkout@v3
+    - name: docker login
+      run: |
+        docker login -u ${DOCKERHUB_USERNAME} -p ${DOCKERHUB_PASSWORD}
+    - name: bigdl-llm-cpu
+      run: |
+        echo "##############################################################"
+        echo "####### bigdl-llm-cpu ########"
+        echo "##############################################################"
+        export image=intelanalytics/bigdl-llm-cpu
+        cd docker/llm/inference/cpu/docker
+        sudo docker build \
+          --no-cache=true \
+          --build-arg http_proxy=${HTTP_PROXY} \
+          --build-arg https_proxy=${HTTPS_PROXY} \
+          --build-arg no_proxy=${NO_PROXY} \
+          --build-arg BASE_IMAGE_NAME=${base_image} \
+          --build-arg BASE_IMAGE_TAG=${TAG} \
+          -t ${image}:${TAG} -f ./Dockerfile .
+        sudo docker push ${image}:${TAG}
+        sudo docker tag ${image}:${TAG} 10.239.45.10/arda/${image}:${TAG}
+        sudo docker push 10.239.45.10/arda/${image}:${TAG}
+        sudo docker rmi -f ${image}:${TAG} 10.239.45.10/arda/${image}:${TAG}
+
   bigdl-ppml-gramine-base:
     if: ${{ github.event.inputs.artifact == 'bigdl-ppml-gramine-base' || github.event.inputs.artifact == 'all' }}
     runs-on: [self-hosted, Shire]

.github/workflows/manually_build_for_testing.yml

@@ -14,6 +14,7 @@ on:
         type: choice
         options:
         - all
+        - bigdl-llm-cpu
         - bigdl-ppml-gramine-base
         - bigdl-ppml-trusted-bigdl-llm-gramine-base
         - bigdl-ppml-trusted-bigdl-llm-gramine-ref
@@ -51,6 +52,36 @@ permissions:
   packages: write
 
 jobs:
+    bigdl-llm-cpu:
+    if: ${{ github.event.inputs.artifact == 'bigdl-llm-cpu' || github.event.inputs.artifact == 'all' }}
+    runs-on: [self-hosted, Shire]
+    steps:
+    - uses: actions/checkout@v3
+      with:
+        ref: ${{ github.event.inputs.sha }}
+    - name: docker login
+      run: |
+        docker login -u ${DOCKERHUB_USERNAME} -p ${DOCKERHUB_PASSWORD}
+    - name: bigdl-llm-cpu
+      run: |
+        echo "##############################################################"
+        echo "####### bigdl-llm-cpu ########"
+        echo "##############################################################"
+        export image=intelanalytics/bigdl-llm-cpu
+        cd docker/llm/inference/cpu/docker
+        sudo docker build \
+          --no-cache=true \
+          --build-arg http_proxy=${HTTP_PROXY} \
+          --build-arg https_proxy=${HTTPS_PROXY} \
+          --build-arg no_proxy=${NO_PROXY} \
+          --build-arg BASE_IMAGE_NAME=${base_image} \
+          --build-arg BASE_IMAGE_TAG=${TAG} \
+          -t ${image}:${TAG} -f ./Dockerfile .
+        sudo docker push ${image}:${TAG}
+        sudo docker tag ${image}:${TAG} 10.239.45.10/arda/${image}:${TAG}
+        sudo docker push 10.239.45.10/arda/${image}:${TAG}
+        sudo docker rmi -f ${image}:${TAG} 10.239.45.10/arda/${image}:${TAG}
+
   bigdl-ppml-gramine-base:
     if: ${{ github.event.inputs.artifact == 'bigdl-ppml-gramine-base' || github.event.inputs.artifact == 'all' }}
     runs-on: [self-hosted, Shire]

docker/llm/inference/cpu/docker/Dockerfile

@@ -14,11 +14,15 @@ RUN env DEBIAN_FRONTEND=noninteractive apt-get update && \
     ln -s /usr/bin/python3 /usr/bin/python && \
     apt-get install -y python3-pip python3.9-dev python3-wheel python3.9-distutils && \
     curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && \
-    # Install FastChat from source requires PEP 660 support
+# Install FastChat from source requires PEP 660 support
     python3 get-pip.py && \
     rm get-pip.py && \
     pip install --upgrade requests argparse urllib3 && \
+    pip3 install --no-cache-dir --upgrade torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu && \
     pip install --pre --upgrade bigdl-llm[all] && \
-    pip install --pre --upgrade bigdl-nano
+    pip install --pre --upgrade bigdl-nano && \
+# Download chat.py script
+    wget -P /root https://raw.githubusercontent.com/intel-analytics/BigDL/main/python/llm/portable-executable/chat.py && \
+    export PYTHONUNBUFFERED=1
 
 ENTRYPOINT ["/bin/bash"]