docker/Dockerfile-base

ARG CUDA_VERSION="11.8.0"
ARG CUDNN_VERSION="8"
ARG UBUNTU_VERSION="22.04"
ARG MAX_JOBS=4

FROM nvidia/cuda:$CUDA_VERSION-cudnn$CUDNN_VERSION-devel-ubuntu$UBUNTU_VERSION as base-builder

ENV PATH="/root/miniconda3/bin:${PATH}"

ARG PYTHON_VERSION="3.9"
ARG PYTORCH_VERSION="2.0.1"
ARG CUDA="118"

ENV PYTHON_VERSION=$PYTHON_VERSION

RUN apt-get update
RUN apt-get install -y wget git build-essential ninja-build git-lfs libaio-dev && rm -rf /var/lib/apt/lists/*

RUN wget \
    https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh \
    && mkdir /root/.conda \
    && bash Miniconda3-latest-Linux-x86_64.sh -b \
    && rm -f Miniconda3-latest-Linux-x86_64.sh

RUN conda create -n "py${PYTHON_VERSION}" python="${PYTHON_VERSION}"

ENV PATH="/root/miniconda3/envs/py${PYTHON_VERSION}/bin:${PATH}"

WORKDIR /workspace

RUN python3 -m pip install --upgrade pip && pip3 install packaging && \
    python3 -m pip install --no-cache-dir -U torch==${PYTORCH_VERSION}+cu${CUDA} --extra-index-url https://download.pytorch.org/whl/cu$CUDA

FROM base-builder AS deepspeed-builder

ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"

WORKDIR /workspace

RUN git clone https://github.com/microsoft/DeepSpeed.git && \
    cd DeepSpeed && \
    MAX_CONCURRENCY=8 DS_BUILD_SPARSE_ATTN=0 DS_BUILD_OPS=1 DS_BUILD_EVOFORMER_ATTN=0 python3 setup.py bdist_wheel

FROM base-builder AS bnb-builder

WORKDIR /workspace
ARG CUDA="118"
ENV CUDA=$CUDA

RUN git clone https://github.com/TimDettmers/bitsandbytes.git && \
    cd bitsandbytes && \
    CUDA_VERSION=$CUDA make cuda11x && \
    python setup.py bdist_wheel

FROM base-builder

ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
ENV TORCH_CUDA_ARCH_LIST=$TORCH_CUDA_ARCH_LIST

# recompile apex
RUN python3 -m pip uninstall -y apex
RUN git clone https://github.com/NVIDIA/apex
#  `MAX_JOBS=1` disables parallel building to avoid cpu memory OOM when building image on GitHub Action (standard) runners
RUN cd apex && MAX_JOBS=1 python3 -m pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" ./

RUN mkdir -p /workspace/builds
COPY --from=bnb-builder /workspace/bitsandbytes /workspace/builds/bitsandbytes

RUN mkdir -p /workspace/wheels/bitsandbytes
COPY --from=deepspeed-builder /workspace/DeepSpeed/dist/deepspeed-*.whl wheels
COPY --from=bnb-builder /workspace/bitsandbytes/dist/bitsandbytes-*.whl wheels
COPY --from=bnb-builder /workspace/bitsandbytes/bitsandbytes/libbitsandbytes*.so wheels/bitsandbytes

RUN pip3 install wheels/deepspeed-*.whl
RUN cd /workspace/builds/bitsandbytes && python3 setup.py install
RUN git lfs install --skip-repo
RUN pip3 install awscli && \
    # The base image ships with `pydantic==1.8.2` which is not working
    pip3 install -U --no-cache-dir pydantic==1.10.10