ARG CUDA_ARCH_LIST="75-real;80-real;86-real;89-real;90-real"
ARG OMPI_VERSION="4.1.7rc1"

# Build dependencies resolver stage
FROM lukemathwalker/cargo-chef:latest AS chef
WORKDIR /usr/src/text-generation-inference/backends/trtllm

FROM chef AS planner
COPY . .
RUN cargo chef prepare --recipe-path recipe.json

# CUDA dependent dependencies resolver stage
FROM nvidia/cuda:12.6.3-cudnn-devel-ubuntu24.04 AS cuda-builder

RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
    --mount=type=cache,target=/var/lib/apt,sharing=locked \
    apt update && apt install -y \
    build-essential \
    cmake \
    curl \
    gcc-14  \
    g++-14 \
    git \
    git-lfs \
    libssl-dev \
    libucx-dev \
    ninja-build \
    pkg-config \
    pipx \
    python3 \
    python3-dev \
    python3-setuptools \
    tar \
    wget && \
    pipx ensurepath

ENV TGI_INSTALL_PREFIX=/usr/local/tgi
ENV TENSORRT_INSTALL_PREFIX=/usr/local/tensorrt

# Install OpenMPI
FROM cuda-builder AS mpi-builder
ARG OMPI_VERSION

ENV OMPI_TARBALL_FILENAME="openmpi-$OMPI_VERSION.tar.bz2"
RUN wget "https://download.open-mpi.org/release/open-mpi/v4.1/$OMPI_TARBALL_FILENAME" -P /opt/src && \
    mkdir /usr/src/mpi && \
    tar -xf "/opt/src/$OMPI_TARBALL_FILENAME" -C /usr/src/mpi --strip-components=1 && \
    cd /usr/src/mpi && \
    ./configure --prefix=/usr/local/mpi --with-cuda=/usr/local/cuda --with-slurm && \
    make -j all && \
    make install && \
    rm -rf "/opt/src/$OMPI_TARBALL_FILENAME"

# Install TensorRT
FROM cuda-builder AS trt-builder
COPY backends/trtllm/scripts/install_tensorrt.sh /opt/install_tensorrt.sh
RUN chmod +x /opt/install_tensorrt.sh && \
    /opt/install_tensorrt.sh

# Build Backend
FROM cuda-builder AS tgi-builder
WORKDIR /usr/src/text-generation-inference

# Install Rust
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | bash -s -- -y && \
    chmod -R a+w /root/.rustup && \
    chmod -R a+w /root/.cargo

ENV PATH="/root/.cargo/bin:$PATH"
RUN cargo install cargo-chef

COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi

ENV MPI_HOME=/usr/local/mpi