mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-24 08:22:07 +00:00
ea7f4082c4
* misc(cmake) update dependencies * feat(hardware) enable new hardware.hpp and unittests * test(ctest) enable address sanitizer * feat(backend): initial rewrite of the backend for simplicity * feat(backend): remove all the logs from hardware.hpp * feat(backend): added some logging * feat(backend): enable compiler warning if support for RVO not applying * feat(backend): missing return statement * feat(backend): introduce backend_workspace_t to store precomputed information from the engine folder * feat(backend): delete previous backend impl * feat(backend): more impl * feat(backend): use latest trtllm main version to have g++ >= 13 compatibility * feat(backend): allow overriding which Python to use * feat(backend): fix backend_exception_t -> backend_error_t naming * feat(backend): impl missing generation_step_t as return value of pull_tokens * feat(backend): make backend_workspace_t::engines_folder constexpr * feat(backend): fix main.rs retrieving the tokenizer * feat(backend): add guard to multiple header definitions * test(backend): add more unittest * feat(backend): remove constexpr from par * feat(backend): remove constexpig * test(backend): more test coverage * chore(trtllm): update dependency towards 0.15.0 * effectively cancel the request on the executor * feat(backend) fix moving backend when pulling * feat(backend): make sure we can easily cancel request on the executor * feat(backend): fix missing "0" field access * misc(backend): fix reborrowing Pin<&mut T> as described in the doc https://doc.rust-lang.org/stable/std/pin/struct.Pin.html#method.as_mut * chore: Add doc and CI for TRTLLM (#2799) * chore: Add doc and CI for TRTLLM * chore: Add doc and CI for TRTLLM * chore: Add doc and CI for TRTLLM * chore: Add doc and CI for TRTLLM * doc: Formatting * misc(backend): indent --------- Co-authored-by: Hugo Larcher <hugo.larcher@huggingface.co>
114 lines
3.8 KiB
Plaintext
114 lines
3.8 KiB
Plaintext
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:$PATH"
|
|
RUN cargo install cargo-chef
|
|
|
|
# Cache dependencies
|
|
COPY --from=planner /usr/src/text-generation-inference/backends/trtllm/recipe.json .
|
|
RUN cargo chef cook --release --recipe-path recipe.json
|
|
|
|
# Build actual TGI
|
|
ARG CUDA_ARCH_LIST
|
|
ENV CMAKE_PREFIX_PATH="/usr/local/mpi:/usr/local/tensorrt:$CMAKE_PREFIX_PATH"
|
|
ENV LD_LIBRARY_PATH="/usr/local/mpi/lib:$LD_LIBRARY_PATH"
|
|
ENV PKG_CONFIG_PATH="/usr/local/mpi/lib/pkgconfig:$PKG_CONFIG_PATH"
|
|
|
|
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 "$TGI_INSTALL_PREFIX/lib" && \
|
|
cd backends/trtllm && \
|
|
CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --release
|
|
|
|
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
|
|
|
|
FROM runtime
|
|
|
|
LABEL co.huggingface.vendor="Hugging Face Inc."
|
|
LABEL org.opencontainers.image.authors="hardware@hf.co"
|
|
|
|
ENTRYPOINT ["./text-generation-launcher"]
|
|
CMD ["--executor-worker", "/usr/local/tgi/bin/executorWorker"]
|