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

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="2.0.0"
ARG CUDA="cu118"

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==${PYTORCH} torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/$CUDA


FROM base-builder AS flash-attn-builder

WORKDIR /workspace

ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"

RUN git clone https://github.com/HazyResearch/flash-attention.git && \
    cd flash-attention && \
    python3 setup.py bdist_wheel

FROM base-builder AS deepspeed-builder

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 python3 setup.py bdist_wheel

FROM base-builder

RUN mkdir /workspace/wheels
COPY --from=deepspeed-builder /workspace/DeepSpeed/dist/deepspeed-*.whl wheels
COPY --from=flash-attn-builder /workspace/flash-attention/dist/flash_attn-*.whl wheels

RUN pip3 install.sh wheels/deepspeed-*.whl wheels/flash_attn-*.whl