text-generation-inference/backends/trtllm/Dockerfile
2024-07-22 14:42:43 +00:00

64 lines
2.1 KiB
Docker

ARG CUDA_ARCH_LIST="75-real;80-real;86-real;89-real;90-real"
ARG INSTALL_PREFIX="/usr/local/tgi
ARG TENSORRT_ROOT_DIR="/usr/local/tensorrt
# Build dependencies resolver stage
FROM lukemathwalker/cargo-chef:latest as chef
WORKDIR /usr/src/text-generation-inference
FROM chef as planner
COPY . .
RUN cargo chef prepare --recipe-path recipe.json
# CUDA dependent dependencies resolver stage
FROM nvcr.io/nvidia/pytorch:24.05-py3 as cuda-builder
RUN apt update && apt install -y \
cmake \
gcc \
g++ \
git \
git-lfs \
ninja-build
# Install TensorRT
COPY backends/trtllm/scripts/install_tensorrt.sh /opt/install_tensorrt.sh
RUN chmod +x /opt/install_tensorrt.sh && \
/opt/install_tensorrt.sh
# Install Rust
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | bash -s -- -y && \
chmod -R a+w $HOME/.rustup && \
chmod -R a+w $HOME/.cargo
ENV PATH="/root/.cargo/bin:$PATH"
RUN cargo install cargo-chef
# Backend build step
WORKDIR /usr/src/text-generation-inference
# Cache dependencies
COPY --from=planner /usr/src/text-generation-inference/recipe.json .
RUN cargo chef cook --release --recipe-path recipe.json
ENV LD_LIBRARY_PATH="/usr/local/mpi/lib:$LD_LIBRARY_PATH"
# Build actual TGI
ENV PKG_CONFIG_PATH="/usr/local/mpi/lib/pkgconfig:$PKG_CONFIG_PATH"
ENV CMAKE_INSTALL_PREFIX="/usr/local/tgi"
COPY . .
RUN mkdir /usr/local/tgi && mkdir /usr/local/tgi/include && mkdir /usr/local/tgi/lib && \
cargo build --release --bin text-generation-backends-trtllm
FROM nvcr.io/nvidia/pytorch:24.05-py3
WORKDIR /usr/local/tgi/bin
ENV LD_LIBRARY_PATH="usr/local/tgi/lib:$LD_LIBRARY_PATH"
RUN ln -s /usr/local/cuda/lib64/stubs/libcuda.so /usr/local/cuda/lib64/stubs/libcuda.so.1 && \
ln -s /usr/local/cuda/lib64/stubs/libnvidia-ml.so /usr/local/cuda/lib64/stubs/libnvidia-ml.so.1
COPY --from=cuda-builder /usr/local/tensorrt /usr/local/tensorrt
COPY --from=cuda-builder /usr/local/tgi /usr/local/tgi
COPY --from=cuda-builder /usr/src/text-generation-inference/target/release/text-generation-backends-trtllm /usr/local/tgi/bin/text-generation-launcher