docker/Dockerfile.rocm7

# default base image
ARG REMOTE_VLLM="1"
ARG COMMON_WORKDIR=/app
ARG BASE_IMAGE=rocm/vllm-dev:base_rocm7_0930_rc1_20250916_tuned_20250917

FROM ${BASE_IMAGE} AS base

ARG ARG_PYTORCH_ROCM_ARCH
ENV PYTORCH_ROCM_ARCH=${ARG_PYTORCH_ROCM_ARCH:-${PYTORCH_ROCM_ARCH}}

# 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)"
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/ROCm/vllm.git"
#ARG VLLM_BRANCH="main"
ARG VLLM_REPO=https://github.com/HollowMan6/vllm.git
ARG VLLM_BRANCH="sleep_amd"
ONBUILD RUN git clone ${VLLM_REPO} \
            && cd vllm \
            && git checkout ${VLLM_BRANCH}
FROM fetch_vllm_${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  \
    && ln -sf /opt/rocm/lib/libamdhip64.so /usr/lib/libamdhip64.so \
    && VLLM_TARGET_DEVICE=rocm ROCM_PATH=/opt/rocm/ VLLM_GPU_LANG=HIP SETUPTOOLS_SCM_PRETEND_VERSION=0.8.4.dev python3 setup.py bdist_wheel --dist-dir=dist
    #&& 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/.buildkite /.buildkite

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

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

# Install vLLM
RUN --mount=type=bind,from=export_vllm,src=/,target=/install \
    cd /install \
    && pip install -U -r requirements/rocm.txt \
    && pip install -U -r requirements/rocm-test.txt \
    && pip uninstall -y vllm \
    && pip 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 \
    && rm -rf vllm \
    && python3 -m pip install -e tests/vllm_test_utils \
    && python3 -m pip install lm-eval[api]==0.4.4 \
    && python3 -m pip install pytest-shard

# -----------------------
# 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 python3 -m pip install --upgrade huggingface-hub[cli]

# Install vLLM
RUN --mount=type=bind,from=export_vllm,src=/,target=/install \
    cd /install \
    && pip install -U -r requirements/rocm.txt \
    && pip uninstall -y vllm \
    && pip install *.whl

ARG COMMON_WORKDIR

# 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

ENV RAY_EXPERIMENTAL_NOSET_ROCR_VISIBLE_DEVICES=1
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

# -----------------------
# Install verl
RUN pip install "tensordict==0.6.2" --no-deps && \
    pip install accelerate \
    codetiming \
    datasets \
    dill \
    hydra-core \
    liger-kernel \
    numpy \
    pandas \
    peft \
    "pyarrow>=15.0.0" \
    pylatexenc \
    torchdata \
    wandb \
    orjson \
    pybind11

WORKDIR /workspace/
RUN git clone https://github.com/volcengine/verl.git && \
    cd verl && \
    pip install -e .

CMD ["/bin/bash"]