hf_text-generation-inference/Dockerfile.trtllm

24 lines
1.0 KiB
Docker

# All the tooling for CUDA
FROM nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04 AS cuda-builder
WORKDIR /usr/src/tgi/backends/trtllm
RUN apt update && apt install -y cmake git git-lfs gcc g++ ninja-build libopenmpi-dev python3-dev python3-pip wget
COPY . /usr/src/tgi
RUN chmod +x scripts/install_tensorrt.sh && scripts/install_tensorrt.sh
RUN cmake -G Ninja -B build -DTRT_LIB_DIR=/usr/local/tensorrt/lib -DTRT_INCLUDE_DIR=/usr/local/tensorrt/include .
RUN cmake --build build --parallel -t tgi_trtllm_backend_impl
# All the tooling for Rust
FROM lukemathwalker/cargo-chef:latest-rust-1.79 AS chef
WORKDIR /usr/src
# Include CUDA related libraries and tools to the Rust based image
COPY --from=cuda-builder /usr/local/cuda /usr/local/cuda
COPY --from=cuda-builder /usr/local/tensorrt /usr/local/tensorrt
COPY --from=cuda-builder /usr/src/tgi/backends/trtllm/build /usr/local/tgi/trtllm/build
ENV PATH=/usr/local/cuda/bin:$PATH
ENV LD_LIBRARY_PATH=/usr/local/tensorrt/lib:$LD_LIBRARY_PATH
RUN apt update && apt install -y cmake git gcc g++ ninja-build libopenmpi3