Dockerfile.rocm

# default base image
ARG REMOTE_VLLM="0"
ARG COMMON_WORKDIR=/app
ARG BASE_IMAGE=rocm/vllm-dev:base

FROM ${BASE_IMAGE} AS base

ARG ARG_PYTORCH_ROCM_ARCH
ENV PYTORCH_ROCM_ARCH=${ARG_PYTORCH_ROCM_ARCH:-${PYTORCH_ROCM_ARCH}}
ENV RAY_EXPERIMENTAL_NOSET_ROCR_VISIBLE_DEVICES=1
ENV RAY_EXPERIMENTAL_NOSET_HIP_VISIBLE_DEVICES=1

# Install some basic utilities
RUN apt-get update -q -y && apt-get install -q -y \
    sqlite3 libsqlite3-dev libfmt-dev libmsgpack-dev libsuitesparse-dev \
    apt-transport-https ca-certificates wget curl
# Remove sccache
RUN python3 -m pip install --upgrade pip
RUN apt-get purge -y sccache; python3 -m pip uninstall -y sccache; rm -f "$(which sccache)"

# Install UV
RUN curl -LsSf https://astral.sh/uv/install.sh | env UV_INSTALL_DIR="/usr/local/bin" sh

# This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out
# Reference: https://github.com/astral-sh/uv/pull/1694
ENV UV_HTTP_TIMEOUT=500
ENV UV_INDEX_STRATEGY="unsafe-best-match"
# Use copy mode to avoid hardlink failures with Docker cache mounts
ENV UV_LINK_MODE=copy

ARG COMMON_WORKDIR
WORKDIR ${COMMON_WORKDIR}


# -----------------------
# vLLM fetch stages
FROM base AS fetch_vllm_0
ONBUILD COPY ./ vllm/
FROM base AS fetch_vllm_1
ARG VLLM_REPO="https://github.com/vllm-project/vllm.git"
ARG VLLM_BRANCH="main"
ENV VLLM_REPO=${VLLM_REPO}
ENV VLLM_BRANCH=${VLLM_BRANCH}
ONBUILD RUN git clone ${VLLM_REPO} \
	    && cd vllm \
	    && git fetch -v --prune -- origin ${VLLM_BRANCH} \
	    && git checkout FETCH_HEAD \
        && if [ ${VLLM_REPO} != "https://github.com/vllm-project/vllm.git" ] ; then \
               git remote add upstream "https://github.com/vllm-project/vllm.git" \
               && git fetch upstream ; fi
FROM fetch_vllm_${REMOTE_VLLM} AS fetch_vllm

# -----------------------
# vLLM build stages
FROM fetch_vllm AS build_vllm
# Build vLLM
RUN cd vllm \
    && python3 -m pip install -r requirements/rocm.txt \
    && python3 setup.py clean --all  \
    && python3 setup.py bdist_wheel --dist-dir=dist
FROM scratch AS export_vllm
ARG COMMON_WORKDIR
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/dist/*.whl /
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/requirements /requirements
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/benchmarks /benchmarks
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/tests /tests
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/examples /examples
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/docker/Dockerfile.rocm /docker/
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/.buildkite /.buildkite
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/vllm/v1 /vllm_v1

# -----------------------
# RIXL/UCX build stages
FROM base AS build_rixl
ARG RIXL_BRANCH="f33a5599"
ARG RIXL_REPO="https://github.com/ROCm/RIXL.git"
ARG UCX_BRANCH="da3fac2a"
ARG UCX_REPO="https://github.com/ROCm/ucx.git"
ENV ROCM_PATH=/opt/rocm
ENV UCX_HOME=/usr/local/ucx
ENV RIXL_HOME=/usr/local/rixl
ENV RIXL_BENCH_HOME=/usr/local/rixl_bench

# RIXL build system dependences and RDMA support
RUN apt-get -y update && apt-get -y install autoconf libtool pkg-config \
    libgrpc-dev \
    libgrpc++-dev \
    libprotobuf-dev \
    protobuf-compiler-grpc \
    libcpprest-dev \
    libaio-dev \
    librdmacm1 \
    librdmacm-dev \
    libibverbs1 \
    libibverbs-dev \
    ibverbs-utils \
    rdmacm-utils \
    ibverbs-providers \
    && rm -rf /var/lib/apt/lists/*

RUN uv pip install --system meson auditwheel patchelf tomlkit

RUN cd /usr/local/src && \
    git clone ${UCX_REPO} &&  \
    cd ucx  && \
    git checkout ${UCX_BRANCH} && \
    ./autogen.sh && \
    mkdir build && cd build && \
    ../configure \
        --prefix=/usr/local/ucx \
        --enable-shared \
        --disable-static \
        --disable-doxygen-doc \
        --enable-optimizations \
        --enable-devel-headers \
        --with-rocm=/opt/rocm \
        --with-verbs \
        --with-dm \
        --enable-mt && \
    make -j && \
    make install

ENV PATH=/usr/local/ucx/bin:$PATH
ENV LD_LIBRARY_PATH=${UCX_HOME}/lib:${LD_LIBRARY_PATH}

RUN git clone ${RIXL_REPO} /opt/rixl && \
    cd /opt/rixl && \
    git checkout ${RIXL_BRANCH} && \
    meson setup build --prefix=${RIXL_HOME} \
                     -Ducx_path=${UCX_HOME} \
                     -Drocm_path=${ROCM_PATH} && \
    cd build && \
    ninja && \
    ninja install

# Generate RIXL wheel
RUN cd /opt/rixl && mkdir -p /app/install && \
    ./contrib/build-wheel.sh \
        --output-dir /app/install \
        --rocm-dir ${ROCM_PATH} \
        --ucx-plugins-dir ${UCX_HOME}/lib/ucx \
        --nixl-plugins-dir ${RIXL_HOME}/lib/x86_64-linux-gnu/plugins

# -----------------------
# Test vLLM image
FROM base AS test

RUN python3 -m pip install --upgrade pip && rm -rf /var/lib/apt/lists/*

# Install vLLM using uv (inherited from base stage)
# Note: No -U flag to avoid upgrading PyTorch ROCm to CUDA version
RUN --mount=type=bind,from=export_vllm,src=/,target=/install \
    --mount=type=cache,target=/root/.cache/uv \
    cd /install \
    && uv pip install --system -r requirements/rocm.txt \
    && uv pip install --system -r requirements/rocm-test.txt \
    && pip uninstall -y vllm \
    && uv pip install --system *.whl

# Install RIXL wheel
RUN --mount=type=bind,from=build_rixl,src=/app/install,target=/rixl_install \
    uv pip install --system /rixl_install/*.whl

WORKDIR /vllm-workspace
ARG COMMON_WORKDIR
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm /vllm-workspace

# install development dependencies (for testing)
RUN cd /vllm-workspace \
    && python3 -m pip install -e tests/vllm_test_utils \
    && python3 -m pip install pytest-shard

# enable fast downloads from hf (for testing)
RUN --mount=type=cache,target=/root/.cache/uv \
    uv pip install --system hf_transfer
ENV HF_HUB_ENABLE_HF_TRANSFER=1

# install audio decode package `torchcodec` from source (required due to 
# ROCm and torch version mismatch) for tests with datasets package
COPY tools/install_torchcodec_rocm.sh /tmp/install_torchcodec.sh
RUN bash /tmp/install_torchcodec.sh \
    && rm /tmp/install_torchcodec.sh \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

# Copy in the v1 package (for python-only install test group)
COPY --from=export_vllm /vllm_v1 /usr/local/lib/python${PYTHON_VERSION}/dist-packages/vllm/v1

# Source code is used in the `python_only_compile.sh` test
# We hide it inside `src/` so that this source code
# will not be imported by other tests
RUN mkdir src && mv vllm src/vllm

# -----------------------
# Final vLLM image
FROM base AS final

RUN python3 -m pip install --upgrade pip && rm -rf /var/lib/apt/lists/*
# Error related to odd state for numpy 1.20.3 where there is no METADATA etc, but an extra LICENSES_bundled.txt.
# Manually remove it so that later steps of numpy upgrade can continue
RUN case "$(which python3)" in \
        *"/opt/conda/envs/py_3.9"*) \
            rm -rf /opt/conda/envs/py_3.9/lib/python3.9/site-packages/numpy-1.20.3.dist-info/;; \
        *) ;; esac

RUN --mount=type=cache,target=/root/.cache/uv \
    uv pip install --system --upgrade huggingface-hub[cli]

# Install vLLM using uv (inherited from base stage)
# Note: No -U flag to avoid upgrading PyTorch ROCm to CUDA version
RUN --mount=type=bind,from=export_vllm,src=/,target=/install \
    --mount=type=cache,target=/root/.cache/uv \
    cd /install \
    && uv pip install --system -r requirements/rocm.txt \
    && pip uninstall -y vllm \
    && uv pip install --system *.whl

ARG COMMON_WORKDIR
ARG BASE_IMAGE

# Copy over the benchmark scripts as well
COPY --from=export_vllm /benchmarks ${COMMON_WORKDIR}/vllm/benchmarks
COPY --from=export_vllm /examples ${COMMON_WORKDIR}/vllm/examples
COPY --from=export_vllm /docker ${COMMON_WORKDIR}/vllm/docker

ENV TOKENIZERS_PARALLELISM=false

# ENV that can improve safe tensor loading, and end-to-end time
ENV SAFETENSORS_FAST_GPU=1

# Performance environment variable.
ENV HIP_FORCE_DEV_KERNARG=1

# Workaround for ROCm profiler limits
RUN echo "ROCTRACER_MAX_EVENTS=10000000" > ${COMMON_WORKDIR}/libkineto.conf
ENV KINETO_CONFIG="${COMMON_WORKDIR}/libkineto.conf"
RUN echo "VLLM_BASE_IMAGE=${BASE_IMAGE}" >> ${COMMON_WORKDIR}/versions.txt

CMD ["/bin/bash"]

#Set entrypoint for vllm-openai official images
FROM final As vllm-openai
ENTRYPOINT ["vllm", "serve"]