vllm/Dockerfile.rocm

# Default ROCm 6.2 base image
ARG BASE_IMAGE="rocm/pytorch:rocm6.2_ubuntu20.04_py3.9_pytorch_release_2.3.0"

# Default ROCm ARCHes to build vLLM for.
ARG PYTORCH_ROCM_ARCH="gfx908;gfx90a;gfx942;gfx1100"

# Whether to install CK-based flash-attention
# If 0, will not install flash-attention
ARG BUILD_FA="1"
ARG FA_GFX_ARCHS="gfx90a;gfx942"
ARG FA_BRANCH="3cea2fb"

# Whether to build triton on rocm
ARG BUILD_TRITON="1"
ARG TRITON_BRANCH="e192dba"

### Base image build stage
FROM $BASE_IMAGE AS base

# Import arg(s) defined before this build stage
ARG PYTORCH_ROCM_ARCH

# Install some basic utilities
RUN apt-get update && apt-get install python3 python3-pip -y
RUN apt-get update && apt-get install -y \
    curl \
    ca-certificates \
    sudo \
    git \
    bzip2 \
    libx11-6 \
    build-essential \
    wget \
    unzip \
    tmux \
    ccache \
 && rm -rf /var/lib/apt/lists/*

# When launching the container, mount the code directory to /vllm-workspace
ARG APP_MOUNT=/vllm-workspace
WORKDIR ${APP_MOUNT}

RUN python3 -m pip install --upgrade pip
# Remove sccache so it doesn't interfere with ccache
# TODO: implement sccache support across components
RUN apt-get purge -y sccache; python3 -m pip uninstall -y sccache; rm -f "$(which sccache)"

# Install torch == 2.6.0 on ROCm
RUN --mount=type=cache,target=/root/.cache/pip \
    case "$(ls /opt | grep -Po 'rocm-[0-9]\.[0-9]')" in \
        *"rocm-6.2"*) \
            python3 -m pip uninstall -y torch torchvision \
            && python3 -m pip install --pre \
                torch==2.6.0.dev20240918 \
                'setuptools-scm>=8' \
                torchvision==0.20.0.dev20240918 \
                --extra-index-url https://download.pytorch.org/whl/nightly/rocm6.2;; \
        *) ;; esac

ENV LLVM_SYMBOLIZER_PATH=/opt/rocm/llvm/bin/llvm-symbolizer
ENV PATH=$PATH:/opt/rocm/bin:/libtorch/bin:
ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/rocm/lib/:/libtorch/lib:
ENV CPLUS_INCLUDE_PATH=$CPLUS_INCLUDE_PATH:/libtorch/include:/libtorch/include/torch/csrc/api/include/:/opt/rocm/include/:

ENV PYTORCH_ROCM_ARCH=${PYTORCH_ROCM_ARCH}
ENV CCACHE_DIR=/root/.cache/ccache


### AMD-SMI build stage
FROM base AS build_amdsmi
# Build amdsmi wheel always
RUN cd /opt/rocm/share/amd_smi \
    && python3 -m pip wheel . --wheel-dir=/install


### Flash-Attention wheel build stage
FROM base AS build_fa
ARG BUILD_FA
ARG FA_GFX_ARCHS
ARG FA_BRANCH
# Build ROCm flash-attention wheel if `BUILD_FA = 1`
RUN --mount=type=cache,target=${CCACHE_DIR} \
    if [ "$BUILD_FA" = "1" ]; then \
        mkdir -p libs \
        && cd libs \
        && git clone https://github.com/ROCm/flash-attention.git \
        && cd flash-attention \
        && git checkout "${FA_BRANCH}" \
        && git submodule update --init \
        && GPU_ARCHS="${FA_GFX_ARCHS}" python3 setup.py bdist_wheel --dist-dir=/install; \
    # Create an empty directory otherwise as later build stages expect one
    else mkdir -p /install; \
    fi


### Triton wheel build stage
FROM base AS build_triton
ARG BUILD_TRITON
ARG TRITON_BRANCH
# Build triton wheel if `BUILD_TRITON = 1`
RUN --mount=type=cache,target=${CCACHE_DIR} \
    if [ "$BUILD_TRITON" = "1" ]; then \
    mkdir -p libs \
    && cd libs \
    && python3 -m pip install ninja cmake wheel pybind11 \
    && git clone https://github.com/OpenAI/triton.git \
    && cd triton \
    && git checkout "${TRITON_BRANCH}" \
    && cd python \
    && python3 setup.py bdist_wheel --dist-dir=/install; \
    # Create an empty directory otherwise as later build stages expect one
    else mkdir -p /install; \
    fi


### Final vLLM build stage
FROM base AS final
# Import the vLLM development directory from the build context
COPY . .
ARG GIT_REPO_CHECK=0
RUN --mount=type=bind,source=.git,target=.git \
    if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh ; fi

RUN python3 -m pip install --upgrade pip

# Package upgrades for useful functionality or to avoid dependency issues
RUN --mount=type=cache,target=/root/.cache/pip \
    python3 -m pip install --upgrade numba scipy huggingface-hub[cli] pytest-shard


# Workaround for ray >= 2.10.0
ENV RAY_EXPERIMENTAL_NOSET_ROCR_VISIBLE_DEVICES=1
# Silences the HF Tokenizers warning
ENV TOKENIZERS_PARALLELISM=false

RUN --mount=type=cache,target=${CCACHE_DIR} \
    --mount=type=bind,source=.git,target=.git \
    --mount=type=cache,target=/root/.cache/pip \
    python3 -m pip install -Ur requirements-rocm.txt \
    && python3 setup.py clean --all \
    && python3 setup.py develop

# Copy amdsmi wheel into final image
RUN --mount=type=bind,from=build_amdsmi,src=/install,target=/install \
    mkdir -p libs \
    && cp /install/*.whl libs \
    # Preemptively uninstall to avoid same-version no-installs
    && python3 -m pip uninstall -y amdsmi;

# Copy triton wheel(s) into final image if they were built
RUN --mount=type=bind,from=build_triton,src=/install,target=/install \
    mkdir -p libs \
    && if ls /install/*.whl; then \
        cp /install/*.whl libs \
        # Preemptively uninstall to avoid same-version no-installs
        && python3 -m pip uninstall -y triton; fi

# Copy flash-attn wheel(s) into final image if they were built
RUN --mount=type=bind,from=build_fa,src=/install,target=/install \
    mkdir -p libs \
    && if ls /install/*.whl; then \
        cp /install/*.whl libs \
        # Preemptively uninstall to avoid same-version no-installs
        && python3 -m pip uninstall -y flash-attn; fi

# Install wheels that were built to the final image
RUN --mount=type=cache,target=/root/.cache/pip \
    if ls libs/*.whl; then \
    python3 -m pip install libs/*.whl; fi

CMD ["/bin/bash"]