text-generation-inference/Dockerfile_trtllm

ARG cuda_arch_list="75-real;80-real;86-real;89-real;90-real"
ARG build_type=release
ARG ompi_version=4.1.7
ARG sccache_gha_enabled=no
ARG actions_cache_url=""
ARG actions_runtime_token=""

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

RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
    build-essential \
    cmake \
    curl \
    gcc-14  \
    g++-14 \
    git \
    git-lfs \
    lld \
    libssl-dev \
    libucx-dev \
    libasan8 \
    libubsan1 \
    ninja-build \
    pkg-config \
    pipx \
    python3 \
    python3-dev \
    python3-setuptools \
    tar \
    wget --no-install-recommends && \
    pipx ensurepath

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

# Install OpenMPI
FROM cuda-builder AS mpi-builder
WORKDIR /opt/src/mpi

ARG ompi_version
ENV OMPI_VERSION=${ompi_version}
ENV OMPI_TARBALL_FILENAME=openmpi-${OMPI_VERSION}.tar.bz2
ADD --checksum=sha256:54a33cb7ad81ff0976f15a6cc8003c3922f0f3d8ceed14e1813ef3603f22cd34 \
    https://download.open-mpi.org/release/open-mpi/v4.1/${OMPI_TARBALL_FILENAME} .

RUN tar --strip-components=1 -xf ${OMPI_TARBALL_FILENAME} &&\
    ./configure --prefix=/usr/local/mpi --with-cuda=/usr/local/cuda --with-slurm && \
    make -j all && \
    make install && \
    rm -rf ${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

# Scoped global args reuse
ARG cuda_arch_list
ARG build_type
ARG sccache_gha_enabled
ARG actions_cache_url
ARG actions_runtime_token

# Install Rust
ENV PATH="/root/.cargo/bin:$PATH"
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 && \
    cargo install sccache --locked

ENV LD_LIBRARY_PATH="/usr/local/mpi/lib:$LD_LIBRARY_PATH"
ENV PKG_CONFIG_PATH="/usr/local/mpi/lib/pkgconfig"
ENV CMAKE_PREFIX_PATH="/usr/local/mpi:/usr/local/tensorrt"

ENV USE_LLD_LINKER=ON
ENV CUDA_ARCH_LIST=${cuda_arch_list}

# SCCACHE Specifics args - before finding a better, more generic, way...
ENV SCCACHE_GHA_ENABLED=${sccache_gha_enabled}
ENV ACTIONS_CACHE_URL=${actions_cache_url}
ENV ACTIONS_RUNTIME_TOKEN=${actions_runtime_token}

COPY Cargo.lock Cargo.lock
COPY Cargo.toml Cargo.toml
COPY rust-toolchain.toml rust-toolchain.toml
COPY router router
COPY backends backends
COPY benchmark benchmark
COPY launcher launcher
COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi

ENV RUSTC_WRAPPER=sccache
ENV CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX
RUN export CMAKE_C_COMPILER_LAUNCHER=sccache && \
    export CMAKE_CXX_COMPILER_LAUNCHER=sccache && \
    export CMAKE_CUDA_COMPILER_LAUNCHER=sccache && \
    mkdir $TGI_INSTALL_PREFIX && mkdir "$TGI_INSTALL_PREFIX/include" && mkdir "$TGI_INSTALL_PREFIX/lib" && \
    cargo build --profile ${build_type} --package text-generation-backends-trtllm --bin text-generation-backends-trtllm && \
    sccache --show-stats

FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04 AS runtime
RUN apt update && apt install -y libucx0 pipx python3-minimal python3-dev python3-pip python3-venv && \
    rm -rf /var/lib/{apt,dpkg,cache,log}/ && \
    pipx ensurepath && \
    pipx install --include-deps transformers tokenizers

WORKDIR /usr/local/tgi/bin

ENV PATH=/root/.local/share/pipx/venvs/transformers/bin/:$PATH
ENV LD_LIBRARY_PATH="/usr/local/tgi/lib:/usr/local/mpi/lib:/usr/local/tensorrt/lib:/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH"
ENV TOKENIZERS_PARALLELISM=false
ENV OMPI_MCA_plm_rsh_agent=""

COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi
COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
COPY --from=tgi-builder /usr/local/tgi /usr/local/tgi
COPY --from=tgi-builder /usr/src/text-generation-inference/target/release/text-generation-backends-trtllm /usr/local/tgi/bin/text-generation-launcher

# This is used only for the CI/CD
FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04 AS ci-runtime
RUN apt update && apt install -y libasan8 libubsan1 libucx0 pipx python3-minimal python3-dev python3-pip python3-venv && \
    rm -rf /var/lib/{apt,dpkg,cache,log}/ && \
    pipx ensurepath && \
    pipx install --include-deps transformers tokenizers

WORKDIR /usr/local/tgi/bin

ENV PATH=/root/.local/share/pipx/venvs/transformers/bin/:$PATH
ENV LD_LIBRARY_PATH="/usr/local/tgi/lib:/usr/local/mpi/lib:/usr/local/tensorrt/lib:/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH"
ENV TOKENIZERS_PARALLELISM=false
ENV OMPI_MCA_plm_rsh_agent=""

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

# Basically we copy from target/debug instead of target/release
COPY --from=tgi-builder /usr/src/text-generation-inference/target/debug/text-generation-backends-trtllm /usr/local/tgi/bin/text-generation-launcher

# This is the final image
FROM runtime

LABEL co.huggingface.vendor="Hugging Face Inc."
LABEL org.opencontainers.image.authors="hardware@hf.co"
LABEL org.opencontainers.title="Text-Generation-Inference TensorRT-LLM Backend"

ENTRYPOINT ["./text-generation-launcher"]
CMD ["--executor-worker", "/usr/local/tgi/bin/executorWorker"]