hf_text-generation-inference/Dockerfile_intel

ARG PLATFORM=xpu

FROM lukemathwalker/cargo-chef:latest-rust-1.80 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 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.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


# Text Generation Inference base image for Intel

FROM intel/intel-extension-for-pytorch:2.1.30-xpu AS xpu

USER root
# 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 apt-get update && apt install -y intel-basekit xpu-smi cmake python3-dev ninja-build pciutils

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


WORKDIR /usr/src
RUN wget https://intel-extension-for-pytorch.s3.amazonaws.com/ipex_dev/xpu/torch-2.1.0.post1%2Bcxx11.abi-cp310-cp310-linux_x86_64.whl && pip install torch-2.1.0.post1+cxx11.abi-cp310-cp310-linux_x86_64.whl
RUN pip install https://github.com/intel/intel-xpu-backend-for-triton/releases/download/v2.1.0/triton-2.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout -b distributed origin/dev/distributed

# 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, 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:
ENV PATH=/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

RUN pip uninstall -y intel-extension-for-pytorch && cd intel-extension-for-pytorch && git submodule update --init --recursive && USE_AOT_DEVLIST='pvc' BUILD_SEPARATE_OPS=OFF BUILD_WITH_CPU=OFF USE_XETLA=ON python setup.py install && rm -rf /usr/src/intel-extension-for-pytorch

# 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++ \
    git \
    wget \
    cmake \
    libnuma-dev

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

ARG MAMBA_VERSION=23.1.0-1
ARG PYTHON_VERSION='3.10.10'
# 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 conda install -c conda-forge gperftools mkl

RUN pip install https://download.pytorch.org/whl/nightly/cpu/torch-2.4.0.dev20240612%2Bcpu-cp310-cp310-linux_x86_64.whl
RUN pip install https://download.pytorch.org/whl/nightly/cpu/torchvision-0.19.0.dev20240612%2Bcpu-cp310-cp310-linux_x86_64.whl
RUN pip install https://download.pytorch.org/whl/nightly/cpu/torchaudio-2.4.0.dev20240612%2Bcpu-cp310-cp310-linux_x86_64.whl
RUN pip install triton numa

WORKDIR /usr/src

RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout eda7a7c42df6f9a64e0de9c2b69304ee02f2c32a

RUN git clone https://github.com/intel/torch-ccl.git && cd torch-ccl && git checkout ccl_torch_dev_0131

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/python3.10/site-packages/oneccl_bindings_for_pytorch
ENV I_MPI_ROOT=/opt/conda/lib/python3.10/site-packages/oneccl_bindings_for_pytorch
ENV FI_PROVIDER_PATH=/opt/conda/lib/python3.10/site-packages/oneccl_bindings_for_pytorch/opt/mpi/libfabric/lib/prov:/usr/lib64/libfabric
ENV LD_LIBRARY_PATH=/opt/conda/lib/python3.10/site-packages/oneccl_bindings_for_pytorch/opt/mpi/libfabric/lib:/opt/conda/lib/python3.10/site-packages/oneccl_bindings_for_pytorch/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, 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 USE_PREFIX_CACHING=0
ENV CUDA_GRAPHS=0
ENTRYPOINT ["text-generation-launcher"]
CMD ["--json-output"]