hf_text-generation-inference/Dockerfile_trtllm

149 lines
5.4 KiB
Plaintext

ARG cuda_arch_list="75-real;80-real;86-real;89-real;90-real"
ARG ompi_version="4.1.7rc1"
ARG build_type=release
ARG is_gha_build=false
# 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 \
lld \
libssl-dev \
libucx-dev \
libasan8 \
libubsan1 \
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
ENV PATH="/root/.cargo/bin:$PATH"
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | bash -s -- -y && \
chmod -R a+w /root/.rustup && \
chmod -R a+w /root/.cargo && \
cargo install sccache --locked
# Build actual TGI
ARG build_type
ARG cuda_arch_list
ARG is_gha_build="false"
# SCCACHE Specifics args - before finding a better, more generic, way...
ARG aws_access_key_id
ARG aws_secret_key_id
ARG aws_session_token
ARG sccache_bucket
ARG sccache_s3_key_prefix
ARG sscache_region
ENV CMAKE_PREFIX_PATH="/usr/local/mpi:/usr/local/tensorrt:$CMAKE_PREFIX_PATH"
ENV CUDA_ARCH_LIST=${cuda_arch_list}
ENV IS_GHA_BUILD ${is_gha_build}
ENV LD_LIBRARY_PATH="/usr/local/mpi/lib:$LD_LIBRARY_PATH"
ENV PKG_CONFIG_PATH="/usr/local/mpi/lib/pkgconfig:$PKG_CONFIG_PATH"
ENV USE_LLD_LINKER=ON
COPY . .
COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi
RUN mkdir $TGI_INSTALL_PREFIX && mkdir "$TGI_INSTALL_PREFIX/include" && mkdir "$TGI_INSTALL_PREFIX/lib" && \
python3 scripts/setup_sccache.py --is-gha-build ${is_gha_build} -k ${aws_access_key_id} -s ${aws_secret_key_id} -t ${aws_session_token} -b ${sccache_bucket} -r ${sscache_region} -p ${sccache_s3_key_prefix } && \
RUSTC_WRAPPER=sccache CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --profile ${build_type} --package text-generation-backends-trtllm --bin text-generation-backends-trtllm
FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04 AS runtime
RUN apt update && apt install -y libucx0 pipx python3-minimal python3-dev python3-pip python3-venv && \
rm -rf /var/lib/{apt,dpkg,cache,log}/ && \
pipx ensurepath && \
pipx install --include-deps transformers tokenizers
WORKDIR /usr/local/tgi/bin
ARG build_type
ENV PATH=/root/.local/share/pipx/venvs/transformers/bin/:$PATH
ENV LD_LIBRARY_PATH="/usr/local/tgi/lib:/usr/local/mpi/lib:/usr/local/tensorrt/lib:/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH"
ENV TOKENIZERS_PARALLELISM=false
ENV OMPI_MCA_plm_rsh_agent=""
COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi
COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
COPY --from=tgi-builder /usr/local/tgi /usr/local/tgi
COPY --from=tgi-builder /usr/src/text-generation-inference/target/release/text-generation-backends-trtllm /usr/local/tgi/bin/text-generation-launcher
FROM runtime
LABEL co.huggingface.vendor="Hugging Face Inc."
LABEL org.opencontainers.image.authors="hardware@hf.co"
LABEL org.opencontainers.title="Text-Generation-Inference TensorRT-LLM Backend"
ENTRYPOINT ["./text-generation-launcher"]
CMD ["--executor-worker", "/usr/local/tgi/bin/executorWorker"]
# This is used only for the CI/CD
FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04 AS ci-runtime
RUN apt update && apt install -y libasan8 libubsan1 libucx0 pipx python3-minimal python3-dev python3-pip python3-venv && \
rm -rf /var/lib/{apt,dpkg,cache,log}/ && \
pipx ensurepath && \
pipx install --include-deps transformers tokenizers
WORKDIR /usr/local/tgi/bin
ENV PATH=/root/.local/share/pipx/venvs/transformers/bin/:$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
FROM ci-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 CI/CD"