Dockerfile_dcu

# Rust builder
FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk24.04-py310 as chef
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
ENV PATH /root/.cargo/bin:$PATH
RUN cargo install cargo-chef
WORKDIR /usr/src

ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse

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

FROM chef AS builder

ARG GIT_SHA
ARG DOCKER_LABEL

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 --release --recipe-path recipe.json

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

# Text Generation Inference base image for RoCm
FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk24.04-py310 as base
# Need hyhal while compiling
WORKDIR /opt
RUN wget https://cancon.hpccube.com:65024/directlink/1/DTK-23.10.1/hyhal.tar.gz && \
    tar -xzf hyhal.tar.gz -C /opt

ENV LD_LIBRARY_PATH /opt/hyhal/lib:/opt/hyhal/lib64:$LD_LIBRARY_PATH
ENV PYTHONPATH /usr/local/lib/python3.10/site-packages:$PYTHONPATH

FROM base AS kernel-builder

# Build vllm kernels
FROM kernel-builder AS vllm-builder
WORKDIR /usr/src
COPY server/vllm/ . 

# Build specific version of vllm
RUN python setup.py build

# Build Transformers CUDA kernels (gpt-neox and bloom)
FROM kernel-builder as custom-kernels-builder
WORKDIR /usr/src
COPY server/custom_kernels/ .
RUN python setup.py build

# Build exllama kernels
FROM kernel-builder as exllama-kernels-builder
WORKDIR /usr/src
COPY server/exllama_kernels/ .

RUN python setup.py build

# Build exllama v2 kernels
FROM kernel-builder as exllamav2-kernels-builder
WORKDIR /usr/src
COPY server/exllamav2_kernels/ .

RUN python setup.py build

FROM base as base-copy

# uninstall exist vllm in base docker image
RUN pip uninstall -y vllm

# Copy builds artifacts from vllm builder
COPY --from=vllm-builder /usr/src/build/lib.linux-x86_64-cpython-310 /usr/local/lib/python3.10/site-packages

# Copy build artifacts from custom kernels builder
COPY --from=custom-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-310 /usr/local/lib/python3.10/site-packages

# Copy build artifacts from exllama kernels builder
COPY --from=exllama-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-310 /usr/local/lib/python3.10/site-packages

# Copy build artifacts from exllamav2 kernels builder
COPY --from=exllamav2-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-310 /usr/local/lib/python3.10/site-packages

# Install server
RUN pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
COPY proto proto
COPY server server
COPY server/Makefile server/Makefile
RUN cd server && \
    make gen-server && \
    pip install -r requirements_rocm.txt && \
    pip install ".[accelerate, peft, outlines]" --no-cache-dir

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

#Remove default hyhal
RUN rm -rf /opt/hyhal /opt/hyhal.tar.gz

# AWS Sagemaker compatible image
# FROM base-copy as sagemaker
# COPY sagemaker-entrypoint.sh entrypoint.sh
# RUN chmod +x entrypoint.sh

# ENTRYPOINT ["./entrypoint.sh"]

# # Final image
# FROM base-copy

# ENTRYPOINT ["text-generation-launcher"]
# CMD ["--json-output"]