update dockerfile to use native python env (#2886)

Author: jingxu10

docker/Dockerfile.compile

@@ -13,7 +13,6 @@ RUN if [ -f /etc/apt/apt.conf.d/proxy.conf ]; then rm /etc/apt/apt.conf.d/proxy.
 RUN apt update && \
     apt full-upgrade -y && \
     DEBIAN_FRONTEND=noninteractive apt install --no-install-recommends -y \
-    sudo \
     ca-certificates \
     git \
     curl \
@@ -22,32 +21,27 @@ RUN apt update && \
     numactl \
     gcc-12 \
     g++-12 \
+    python3 \
+    python3-dev \
+    python3-pip \
     make
 RUN update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 100 && \
     update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-12 100 && \
     update-alternatives --install /usr/bin/cc cc /usr/bin/gcc 100 && \
-    update-alternatives --install /usr/bin/c++ c++ /usr/bin/g++ 100
+    update-alternatives --install /usr/bin/c++ c++ /usr/bin/g++ 100 && \
+    update-alternatives --install /usr/bin/python python /usr/bin/python3 100
 RUN apt clean && \
     rm -rf /var/lib/apt/lists/* && \
     if [ -f /etc/apt/apt.conf.d/proxy.conf ]; then rm /etc/apt/apt.conf.d/proxy.conf; fi
 
-RUN useradd -m ubuntu && \
-    echo 'ubuntu ALL=(ALL) NOPASSWD: ALL' >> /etc/sudoers
-USER ubuntu
-WORKDIR /home/ubuntu
-
-RUN curl -fsSL -v -o miniconda.sh -O https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh  && \
-    bash miniconda.sh -b -p ./miniconda3 && \
-    rm miniconda.sh && \
-    echo "source ~/miniconda3/bin/activate" >> ./.bashrc
+WORKDIR /root
+ENV PATH=/root/.local/bin:${PATH}
 
 FROM base AS dev
-COPY --chown=ubuntu:ubuntu . ./intel-extension-for-pytorch
+COPY . ./intel-extension-for-pytorch
 RUN cp ./intel-extension-for-pytorch/scripts/compile_bundle.sh ./ && \
     sed -i "s/VER_IPEX=.*/VER_IPEX=/" compile_bundle.sh
-RUN . ./miniconda3/bin/activate && \
-    conda create -y -n compile_py310 python=3.10 && conda activate compile_py310 && \
-    bash compile_bundle.sh && \
+RUN CC=gcc CXX=g++ bash compile_bundle.sh && \
     cd intel-extension-for-pytorch && \
     python -m pip install pyyaml && \
     VER_TORCH=$(python tools/yaml_utils.py -f dependency_version.yml -d pytorch -k version) && \
@@ -58,18 +52,11 @@ RUN . ./miniconda3/bin/activate && \
     echo ${VER_TORCH} | grep "dev" > /dev/null; TORCH_DEV=$?; URL_NIGHTLY=""; if [ ${TORCH_DEV} -eq 0 ]; then URL_NIGHTLY="nightly/"; fi; echo "#!/bin/bash\npython -m pip install torch==${VER_TORCH} torchvision==${VER_TORCHVISION} torchaudio==${VER_TORCHAUDIO} --index-url https://download.pytorch.org/whl/${URL_NIGHTLY}cpu" > torch_install.sh
 
 FROM base AS deploy
-COPY --from=dev --chown=ubuntu:ubuntu /home/ubuntu/intel-extension-for-pytorch/dist ./wheels
-COPY --from=dev --chown=ubuntu:ubuntu /home/ubuntu/intel-extension-for-pytorch/tools/get_libstdcpp_lib.sh .
-COPY --from=dev --chown=ubuntu:ubuntu /home/ubuntu/torch_install.sh .
-RUN . ./miniconda3/bin/activate && \
-    conda create -y -n py310 python=3.10 && conda activate py310 && \
-    bash ./torch_install.sh && rm ./torch_install.sh && \
+COPY --from=dev /root/intel-extension-for-pytorch/dist ./wheels
+COPY --from=dev /root/torch_install.sh .
+RUN bash ./torch_install.sh && rm ./torch_install.sh && \
     python -m pip install ./wheels/*.whl && \
     python -m pip install intel-openmp && \
-    conda install -y jemalloc gperftools -c conda-forge && \
     python -m pip cache purge && \
-    conda clean -a -y && \
     rm -rf ./wheels && \
-    echo "conda activate py310" >> ./.bashrc && \
-    ldpreload=$(bash get_libstdcpp_lib.sh) && echo "export LD_PRELOAD=${ldpreload}" >> ./.bashrc && rm get_libstdcpp_lib.sh && \
     echo "echo \"**Note:** For better performance, please consider to launch workloads with command 'ipexrun'.\"" >> ./.bashrc

examples/cpu/inference/python/llm/Dockerfile

@@ -13,55 +13,62 @@ RUN if [ -f /etc/apt/apt.conf.d/proxy.conf ]; then rm /etc/apt/apt.conf.d/proxy.
 RUN apt update && \
     apt full-upgrade -y && \
     DEBIAN_FRONTEND=noninteractive apt install --no-install-recommends -y \
-    sudo \
     ca-certificates \
     git \
     curl \
     wget \
     vim \
+    python3 \
+    python3-dev \
+    python3-pip \
     numactl \
     gcc-12 \
     g++-12 \
-    make
+    make \
+    cmake
 RUN update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 100 && \
     update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-12 100 && \
     update-alternatives --install /usr/bin/cc cc /usr/bin/gcc 100 && \
-    update-alternatives --install /usr/bin/c++ c++ /usr/bin/g++ 100
-RUN apt clean && \
-    rm -rf /var/lib/apt/lists/* && \
-    if [ -f /etc/apt/apt.conf.d/proxy.conf ]; then rm /etc/apt/apt.conf.d/proxy.conf; fi
+    update-alternatives --install /usr/bin/c++ c++ /usr/bin/g++ 100 && \
+    update-alternatives --install /usr/bin/python python /usr/bin/python3 100
 
-RUN useradd -m ubuntu && \
-    echo 'ubuntu ALL=(ALL) NOPASSWD: ALL' >> /etc/sudoers
-USER ubuntu
-WORKDIR /home/ubuntu
-
-RUN curl -fsSL -v -o miniconda.sh -O https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh  && \
-    bash miniconda.sh -b -p ./miniconda3 && \
-    rm miniconda.sh && \
-    echo "source ~/miniconda3/bin/activate" >> ./.bashrc
+WORKDIR /root
+ENV PATH=/root/.local/bin:${PATH}
 
 # --build-arg COMPILE=ON to compile from source
 FROM base AS dev
 ARG COMPILE
-COPY --chown=ubuntu:ubuntu . ./intel-extension-for-pytorch
-RUN . ./miniconda3/bin/activate && \
-    conda create -y -n compile_py310 python=3.10 && conda activate compile_py310 && \
-    cd intel-extension-for-pytorch/examples/cpu/inference/python/llm && \
-    if [ -z ${COMPILE} ]; then bash tools/env_setup.sh 6; else bash tools/env_setup.sh 2; fi
+COPY . ./intel-extension-for-pytorch
+RUN cd intel-extension-for-pytorch/examples/cpu/inference/python/llm && \
+    export CC=gcc && export CXX=g++ && \
+    if [ -z ${COMPILE} ]; then bash tools/env_setup.sh 6; else bash tools/env_setup.sh 2; fi && \
+    unset CC && unset CXX
 
 FROM base AS deploy
-COPY --from=dev --chown=ubuntu:ubuntu /home/ubuntu/intel-extension-for-pytorch/examples/cpu/inference/python/llm ./llm
-RUN rm ./llm/tools/get_libstdcpp_lib.sh
-COPY --from=dev --chown=ubuntu:ubuntu /home/ubuntu/intel-extension-for-pytorch/examples/cpu/inference/python/llm/tools/get_libstdcpp_lib.sh ./llm/tools/get_libstdcpp_lib.sh
-RUN . ./miniconda3/bin/activate && \
-    conda create -y -n py310 python=3.10 && conda activate py310 && \
-    echo "conda activate py310" >> ./.bashrc && \
+RUN apt update && \
+    DEBIAN_FRONTEND=noninteractive apt install --no-install-recommends -y \
+    google-perftools \
+    openssh-server \
+    net-tools && \
+    apt clean && \
+    rm -rf /var/lib/apt/lists/* && \
+    if [ -f /etc/apt/apt.conf.d/proxy.conf ]; then rm /etc/apt/apt.conf.d/proxy.conf; fi
+COPY --from=dev /root/intel-extension-for-pytorch/examples/cpu/inference/python/llm ./llm
+COPY --from=dev /root/intel-extension-for-pytorch/tools/get_libstdcpp_lib.sh ./llm/tools
+RUN cd /usr/lib/x86_64-linux-gnu/ && ln -s libtcmalloc.so.4 libtcmalloc.so && cd && \
     echo "echo \"**Note:** For better performance, please consider to launch workloads with command 'ipexrun'.\"" >> ./.bashrc && \
     cd ./llm && \
     bash tools/env_setup.sh 1 && \
     python -m pip cache purge && \
-    conda clean -a -y && \
-    sudo mv ./oneCCL_release /opt/oneCCL && \
-    sudo chown -R root:root /opt/oneCCL && \
-    sed -i "s|ONECCL_PATH=.*|ONECCL_PATH=/opt/oneCCL|" ./tools/env_activate.sh
+    mv ./oneCCL_release /opt/oneCCL && \
+    chown -R root:root /opt/oneCCL && \
+    sed -i "s|ONECCL_PATH=.*|ONECCL_PATH=/opt/oneCCL|" ./tools/env_activate.sh && \
+    LN=$(grep "Conda environment is not available." -n ./tools/env_activate.sh | cut -d ":" -f 1) && sed -i "${LN}s|.*|    export LD_PRELOAD=\${LD_PRELOAD}:/usr/lib/x86_64-linux-gnu/libtcmalloc.so:/usr/local/lib/libiomp5.so|" ./tools/env_activate.sh
+ARG PORT_SSH=22
+RUN mkdir /var/run/sshd && \
+    sed -i "s/#Port.*/Port ${PORT_SSH}/" /etc/ssh/sshd_config && \
+    echo "service ssh start" >> /root/.bashrc && \
+    ssh-keygen -b 4096 -f /root/.ssh/id_rsa -N "" && \
+    mv /root/.ssh/id_rsa.pub /root/.ssh/authorized_keys && \
+    echo "Host *\n    Port ${PORT_SSH}\n    IdentityFile /root/.ssh/id_rsa\n    StrictHostKeyChecking no" > /root/.ssh/config
+EXPOSE ${PORT_SSH}

examples/cpu/inference/python/llm/tools/env_activate.sh

@@ -16,7 +16,7 @@ if [ $? -eq 0 ]; then
     # Tcmalloc is a recommended malloc implementation that emphasizes fragmentation avoidance and scalable concurrency support.
     export LD_PRELOAD=${LD_PRELOAD}:${CONDA_PREFIX}/lib/libtcmalloc.so
 else
-    echo "Conda environment is not available. You need to set environment variable LD_PRELOAD to dynamic libraries of Intel OpenMP and TcMalloc manually."
+    echo "Conda environment is not available. You need to set environment variable LD_PRELOAD to dynamic libraries of Intel OpenMP and TcMalloc manually if they are not in library search paths."
 fi
 
 ONECCL_PATH=${BASEFOLDER}/../oneCCL_release

examples/cpu/inference/python/llm/tools/env_setup.sh

@@ -32,7 +32,7 @@ if [ ! -f ${WHEELFOLDER}/lm_eval*.whl ] ||
 fi
 
 # Check existance of required Linux commands
-for CMD in conda gcc g++; do
+for CMD in gcc g++; do
     command -v ${CMD} > /dev/null || (echo "Error: Command \"${CMD}\" is required."; exit 1;)
 done
 
@@ -131,12 +131,21 @@ if [ $((${MODE} & 0x02)) -ne 0 ]; then
             echo "         Found GCC version $(gcc -dumpfullversion)"
             echo "         Installing gcc and g++ 12.3 with conda"
             echo ""
-            conda install -y sysroot_linux-64
-            conda install -y gcc==12.3 gxx==12.3 cxx-compiler -c conda-forge
-            if [ -z ${CONDA_BUILD_SYSROOT} ]; then
-                source ${CONDA_PREFIX}/etc/conda/activate.d/activate-gcc_linux-64.sh
-                source ${CONDA_PREFIX}/etc/conda/activate.d/activate-gxx_linux-64.sh
-                source ${CONDA_PREFIX}/etc/conda/activate.d/activate-binutils_linux-64.sh
+            set +e
+            command -v conda > /dev/null
+            EXIST_CONDA=$?
+            set -e
+            if [ ${EXIST_CONDA} -gt 0 ]; then
+                echo "[Error] Command \"conda\" is not available."
+                exit 5
+            else
+                conda install -y sysroot_linux-64
+                conda install -y gcc==12.3 gxx==12.3 cxx-compiler -c conda-forge
+                if [ -z ${CONDA_BUILD_SYSROOT} ]; then
+                    source ${CONDA_PREFIX}/etc/conda/activate.d/activate-gcc_linux-64.sh
+                    source ${CONDA_PREFIX}/etc/conda/activate.d/activate-gxx_linux-64.sh
+                    source ${CONDA_PREFIX}/etc/conda/activate.d/activate-binutils_linux-64.sh
+                fi
             fi
         fi
 
@@ -206,7 +215,15 @@ if [ $((${MODE} & 0x02)) -ne 0 ]; then
     cd intel-extension-for-pytorch/examples/cpu/inference/python/llm
 fi
 if [ $((${MODE} & 0x01)) -ne 0 ]; then
-    conda install -y gperftools -c conda-forge
+    set +e
+    command -v conda > /dev/null
+    EXIST_CONDA=$?
+    set -e
+    if [ ${EXIST_CONDA} -gt 0 ]; then
+        echo "[WARNING] Command \"conda\" is not available. Please install tcmalloc manually."
+    else
+        conda install -y gperftools -c conda-forge
+    fi
     bash ${AUX_INSTALL_SCRIPT}
     python -m pip install ${WHEELFOLDER}/*.whl
     rm -rf ${WHEELFOLDER}

scripts/compile_bundle.sh

@@ -23,7 +23,7 @@ if [ $# -gt 0 ]; then
 fi
 
 # Check existance of required Linux commands
-for CMD in conda git nproc; do
+for CMD in git nproc; do
     command -v ${CMD} > /dev/null || (echo "Error: Command \"${CMD}\" not found." ; exit 1)
 done
 
@@ -97,8 +97,11 @@ function ver_compare() {
     fi
     echo ${RET}
 }
-GCC_CONDA=0
 set +e
+command -v conda > /dev/null
+EXIST_CONDA=$?
+
+GCC_CONDA=0
 command -v gcc > /dev/null
 EXIST_CC=$?
 command -v g++ > /dev/null
@@ -121,7 +124,7 @@ else
         GCC_CONDA=1
     else
         DIR_GCC=$(which gcc)
-        if [[ ${DIR_GCC} =~ ${CONDA_PREFIX} ]]; then
+        if [ ! -z ${CONDA_PREFIX} ] && [[ ${DIR_GCC} =~ ${CONDA_PREFIX} ]]; then
             GCC_CONDA=2
         fi
     fi
@@ -216,6 +219,10 @@ ABI=$(python -c "import torch; print(int(torch._C._GLIBCXX_USE_CXX11_ABI))")
 
 # Compile individual component
 if [ ${GCC_CONDA} -eq 1 ]; then
+    if [ ${EXIST_CONDA} -gt 0 ]; then
+        echo "Command \"conda\" not found. Exit."
+		exit 2
+    fi
     conda install -y sysroot_linux-64
     conda install -y gcc==12.3 gxx==12.3 cxx-compiler -c conda-forge
 fi
@@ -240,7 +247,7 @@ fi
 set +e
 command -v make > /dev/null
 if [ $? -gt 0 ]; then
-    conda install -y make -c conda-forge
+    python -m pip install make
 fi
 set -e