hf_text-generation-inference/Dockerfile_intel

ARG PLATFORM=xpu

FROM lukemathwalker/cargo-chef:latest-rust-1.80.1 AS chef
WORKDIR /usr/src

ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse

FROM chef AS planner
COPY Cargo.lock Cargo.lock
COPY Cargo.toml Cargo.toml
COPY rust-toolchain.toml rust-toolchain.toml
COPY proto proto
COPY benchmark benchmark
COPY router router
COPY backends backends
COPY launcher launcher
RUN cargo chef prepare --recipe-path recipe.json

FROM chef AS builder

RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
    python3.11-dev
RUN PROTOC_ZIP=protoc-21.12-linux-x86_64.zip && \
    curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v21.12/$PROTOC_ZIP && \
    unzip -o $PROTOC_ZIP -d /usr/local bin/protoc && \
    unzip -o $PROTOC_ZIP -d /usr/local 'include/*' && \
    rm -f $PROTOC_ZIP

COPY --from=planner /usr/src/recipe.json recipe.json
RUN cargo chef cook --profile release-opt --recipe-path recipe.json

ARG GIT_SHA
ARG DOCKER_LABEL

COPY Cargo.lock Cargo.lock
COPY Cargo.toml Cargo.toml
COPY rust-toolchain.toml rust-toolchain.toml
COPY proto proto
COPY benchmark benchmark
COPY router router
COPY backends backends
COPY launcher launcher
RUN cargo build --profile release-opt --frozen


# Text Generation Inference base image for Intel

FROM intel/intel-extension-for-pytorch:2.3.110-xpu AS xpu

USER root

ARG MAMBA_VERSION=23.1.0-1
ARG PYTHON_VERSION='3.11.10'
# Automatically set by buildx
ARG TARGETPLATFORM
ENV PATH=/opt/conda/bin:$PATH

# TGI seem to require libssl.so.1.1 instead of libssl.so.3 so we can't use ubuntu 22.04. Ubuntu 20.04 has python==3.8, and TGI requires python>=3.9, hence the need for miniconda.
# Install mamba
# translating Docker's TARGETPLATFORM into mamba arches
RUN case ${TARGETPLATFORM} in \
         "linux/arm64")  MAMBA_ARCH=aarch64  ;; \
         *)              MAMBA_ARCH=x86_64   ;; \
    esac && \
    curl -fsSL -v -o ~/mambaforge.sh -O  "https://github.com/conda-forge/miniforge/releases/download/${MAMBA_VERSION}/Mambaforge-${MAMBA_VERSION}-Linux-${MAMBA_ARCH}.sh"
RUN chmod +x ~/mambaforge.sh && \
    bash ~/mambaforge.sh -b -p /opt/conda && \
    rm ~/mambaforge.sh

RUN case ${TARGETPLATFORM} in \
         "linux/arm64")  exit 1 ;; \
         *)              /opt/conda/bin/conda update -y conda &&  \
                         /opt/conda/bin/conda install -y "python=${PYTHON_VERSION}" ;; \
    esac && \
    /opt/conda/bin/conda clean -ya

# libssl.so.1.1 is not installed on Ubuntu 22.04 by default, install it
RUN wget http://nz2.archive.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2_amd64.deb && \
    dpkg -i ./libssl1.1_1.1.1f-1ubuntu2_amd64.deb

RUN wget -qO - https://repositories.intel.com/gpu/intel-graphics.key | gpg --dearmor | tee /usr/share/keyrings/intel-graphics.gpg > /dev/null

RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB \
| gpg --dearmor | tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null && echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list

RUN echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/intel-for-pytorch-gpu-dev all main" > /tmp/intel-for-pytorch-gpu-dev.list

RUN mv /tmp/intel-for-pytorch-gpu-dev.list /etc/apt/sources.list.d

RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt install -y intel-basekit=2024.2.1-98 xpu-smi cmake ninja-build pciutils intel-pti-dev-0.9

# Text Generation Inference base env
ENV HF_HOME=/data \
    HF_HUB_ENABLE_HF_TRANSFER=1 \
    PORT=80



WORKDIR /usr/src
RUN pip install https://intel-extension-for-pytorch.s3.us-east-1.amazonaws.com/ipex_dev/xpu/torch-2.5.0a0%2Bgite84e33f-cp311-cp311-linux_x86_64.whl --no-cache-dir
RUN pip install https://intel-extension-for-pytorch.s3.us-east-1.amazonaws.com/ipex_dev/xpu/torchaudio-2.5.0a0%2B56bc006-cp311-cp311-linux_x86_64.whl --no-cache-dir
RUN pip install https://intel-extension-for-pytorch.s3.us-east-1.amazonaws.com/ipex_dev/xpu/torchvision-0.20.0a0%2B8e8a208-cp311-cp311-linux_x86_64.whl --no-cache-dir
RUN pip install https://intel-extension-for-pytorch.s3.us-east-1.amazonaws.com/ipex_dev/xpu/intel_extension_for_pytorch-2.5.10%2Bgit9d489a8-cp311-cp311-linux_x86_64.whl --no-cache-dir
RUN pip install https://intel-extension-for-pytorch.s3.us-east-1.amazonaws.com/ipex_dev/xpu/oneccl_bind_pt-2.5.0%2Bxpu-cp311-cp311-linux_x86_64.whl --no-cache-dir

RUN pip install triton-xpu==3.0.0b2 --no-cache-dir

# Install server
COPY proto proto
COPY server server
COPY server/Makefile server/Makefile
RUN cd server && \
    make gen-server && \
    pip install -r requirements_intel.txt && \
    pip install ".[accelerate, compressed-tensors, peft, outlines]" --no-cache-dir

ENV CCL_ROOT=/opt/intel/oneapi/ccl/latest
ENV I_MPI_ROOT=/opt/intel/oneapi/mpi/latest
ENV FI_PROVIDER_PATH=/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/lib/prov:/usr/lib/x86_64-linux-gnu/libfabric
ENV LIBRARY_PATH=/opt/intel/oneapi/mpi/latest/lib:/opt/intel/oneapi/ccl/latest/lib/:/opt/intel/oneapi/mkl/latest/lib/:/opt/intel/oneapi/compiler/latest/lib
ENV LD_LIBRARY_PATH=/opt/intel/oneapi/ccl/latest/lib/:/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/lib:/opt/intel/oneapi/mpi/latest/lib:/opt/intel/oneapi/mkl/latest/lib:/opt/intel/oneapi/compiler/latest/opt/compiler/lib:/opt/intel/oneapi/compiler/latest/lib:/opt/intel/oneapi/lib:/opt/intel/oneapi/lib/intel64:/opt/intel/oneapi/pti/0.9/lib:/opt/conda/lib
ENV PATH=/opt/conda/bin:/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/bin:/opt/intel/oneapi/mpi/latest/bin:/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/bin:/opt/intel/oneapi/mkl/latest/bin/:/opt/intel/oneapi/compiler/latest/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
ENV CCL_ZE_IPC_EXCHANGE=sockets
ENV CMAKE_PREFIX_PATH=/opt/intel/oneapi/mkl/latest/lib/cmake:/opt/intel/oneapi/compiler/latest
ENV CPATH=/opt/intel/oneapi/mpi/latest/include:/opt/intel/oneapi/ccl/latest/include:/opt/intel/oneapi/mkl/latest/include
#ENV TORCH_LLM_ALLREDUCE=1
#ENV CCL_TOPO_FABRIC_VERTEX_CONNECTION_CHECK=0

# Install benchmarker
COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark
# Install router
COPY --from=builder /usr/src/target/release-opt/text-generation-router /usr/local/bin/text-generation-router
# Install launcher
COPY --from=builder /usr/src/target/release-opt/text-generation-launcher /usr/local/bin/text-generation-launcher


# Text Generation Inference base image for Intel-cpu
FROM ubuntu:22.04 AS cpu

RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
    curl \
    ca-certificates \
    make \
    g++-12 \
    gcc-12 \
    git \
    wget \
    cmake \
    libnuma-dev

RUN update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-12 12
RUN update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 12
RUN update-alternatives --install /usr/bin/cc cc /usr/bin/gcc 30
RUN update-alternatives --set cc /usr/bin/gcc

RUN update-alternatives --install /usr/bin/c++ c++ /usr/bin/g++ 30
RUN update-alternatives --set c++ /usr/bin/g++


ENV HUGGINGFACE_HUB_CACHE=/data \
    HF_HUB_ENABLE_HF_TRANSFER=1 \
    PORT=80

ARG MAMBA_VERSION=23.1.0-1
ARG PYTHON_VERSION='3.11.10'
# Automatically set by buildx
ARG TARGETPLATFORM
ENV PATH /opt/conda/bin:$PATH

# TGI seem to require libssl.so.1.1 instead of libssl.so.3 so we can't use ubuntu 22.04. Ubuntu 20.04 has python==3.8, and TGI requires python>=3.9, hence the need for miniconda.
# Install mamba
# translating Docker's TARGETPLATFORM into mamba arches
RUN case ${TARGETPLATFORM} in \
         "linux/arm64")  MAMBA_ARCH=aarch64  ;; \
         *)              MAMBA_ARCH=x86_64   ;; \
    esac && \
    curl -fsSL -v -o ~/mambaforge.sh -O  "https://github.com/conda-forge/miniforge/releases/download/${MAMBA_VERSION}/Mambaforge-${MAMBA_VERSION}-Linux-${MAMBA_ARCH}.sh"
RUN chmod +x ~/mambaforge.sh && \
    bash ~/mambaforge.sh -b -p /opt/conda && \
    rm ~/mambaforge.sh

RUN case ${TARGETPLATFORM} in \
         "linux/arm64")  exit 1 ;; \
         *)              /opt/conda/bin/conda update -y conda &&  \
                         /opt/conda/bin/conda install -y "python=${PYTHON_VERSION}" ;; \
    esac && \
    /opt/conda/bin/conda clean -ya

RUN conda install -c conda-forge gperftools mkl


RUN pip install https://download.pytorch.org/whl/nightly/cpu/torch-2.5.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl
RUN pip install https://download.pytorch.org/whl/nightly/cpu/torchvision-0.20.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl
RUN pip install https://download.pytorch.org/whl/nightly/cpu/torchaudio-2.4.0.dev20240815%2Bcpu-cp311-cp311-linux_x86_64.whl

RUN pip install triton py-libnuma

WORKDIR /usr/src

RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout b7b552baf64283b594665b8687430fe92990e497
RUN git clone https://github.com/intel/torch-ccl.git && cd torch-ccl && git checkout v2.4.0+cpu+rc0

RUN sed -i 's/VERSION_MINOR 6/VERSION_MINOR 5/' intel-extension-for-pytorch/version.txt
RUN cd intel-extension-for-pytorch && git submodule sync && git submodule update --init --recursive && python setup.py install

RUN cd torch-ccl && git submodule sync && git submodule update --init --recursive && pip install .

ENV LD_PRELOAD=/opt/conda/lib/libtcmalloc.so
ENV CCL_ROOT=/opt/conda/lib/python3.11/site-packages/oneccl_bindings_for_pytorch
ENV I_MPI_ROOT=/opt/conda/lib/python3.11/site-packages/oneccl_bindings_for_pytorch
ENV FI_PROVIDER_PATH=/opt/conda/lib/python3.11/site-packages/oneccl_bindings_for_pytorch/opt/mpi/libfabric/lib/prov:/usr/lib64/libfabric
ENV LD_LIBRARY_PATH=/opt/conda/lib/python3.11/site-packages/oneccl_bindings_for_pytorch/opt/mpi/libfabric/lib:/opt/conda/lib/python3.11/site-packages/oneccl_bindings_for_pytorch/lib
ENV LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/opt/conda/lib/"

# Install server
COPY proto proto
COPY server server
COPY server/Makefile server/Makefile
RUN cd server && \
    make gen-server && \
    pip install -r requirements_intel.txt && \
    pip install ".[accelerate, compressed-tensors, peft, outlines]" --no-cache-dir

# Install benchmarker
COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark
# Install router
COPY --from=builder /usr/src/target/release-opt/text-generation-router /usr/local/bin/text-generation-router
# Install launcher
COPY --from=builder /usr/src/target/release-opt/text-generation-launcher /usr/local/bin/text-generation-launcher

FROM ${PLATFORM} AS final
ENV ATTENTION=paged
ENV PREFIX_CACHING=0
ENV PREFILL_CHUNKING=0
ENV CUDA_GRAPHS=0
ENTRYPOINT ["text-generation-launcher"]
CMD ["--json-output"]