Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

make docker linter happy with same capitalization rule

This commit is contained in:
Morgan Funtowicz 2024-07-23 07:42:31 +00:00
parent d9decb4c2c
commit 4c657ca158
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
backends/trtllm/Dockerfile
View File

@ -2,15 +2,15 @@ ARG CUDA_ARCH_LIST="75-real;80-real;86-real;89-real;90-real"
ARG OMPI_VERSION="4.1.6" ARG OMPI_VERSION="4.1.6"
# Build dependencies resolver stage # Build dependencies resolver stage
FROM lukemathwalker/cargo-chef:latest as chef FROM lukemathwalker/cargo-chef:latest AS chef
WORKDIR /usr/src/text-generation-inference WORKDIR /usr/src/text-generation-inference
FROM chef as planner FROM chef AS planner
COPY . . COPY . .
RUN cargo chef prepare --recipe-path recipe.json RUN cargo chef prepare --recipe-path recipe.json
# CUDA dependent dependencies resolver stage # CUDA dependent dependencies resolver stage
FROM nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04 as cuda-builder FROM nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04 AS cuda-builder
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt,sharing=locked \ --mount=type=cache,target=/var/lib/apt,sharing=locked \
@ -34,7 +34,7 @@ ENV TGI_INSTALL_PREFIX=/usr/local/tgi
ENV TENSORRT_INSTALL_PREFIX=/usr/local/tensorrt ENV TENSORRT_INSTALL_PREFIX=/usr/local/tensorrt
# Install OpenMPI # Install OpenMPI
FROM cuda-builder as mpi-builder FROM cuda-builder AS mpi-builder
ARG OMPI_VERSION ARG OMPI_VERSION
ENV OMPI_TARBALL_FILENAME="openmpi-$OMPI_VERSION.tar.bz2" ENV OMPI_TARBALL_FILENAME="openmpi-$OMPI_VERSION.tar.bz2"
@ -48,13 +48,13 @@ RUN wget "https://download.open-mpi.org/release/open-mpi/v4.1/$OMPI_TARBALL_FILE
rm -rf "/opt/src/$OMPI_TARBALL_FILENAME" rm -rf "/opt/src/$OMPI_TARBALL_FILENAME"
# Install TensorRT # Install TensorRT
FROM cuda-builder as trt-builder FROM cuda-builder AS trt-builder
COPY backends/trtllm/scripts/install_tensorrt.sh /opt/install_tensorrt.sh COPY backends/trtllm/scripts/install_tensorrt.sh /opt/install_tensorrt.sh
RUN chmod +x /opt/install_tensorrt.sh && \ RUN chmod +x /opt/install_tensorrt.sh && \
/opt/install_tensorrt.sh /opt/install_tensorrt.sh
# Build Backend # Build Backend
FROM cuda-builder as tgi-builder FROM cuda-builder AS tgi-builder
WORKDIR /usr/src/text-generation-inference WORKDIR /usr/src/text-generation-inference
# Install Rust # Install Rust
@ -81,7 +81,7 @@ 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" && \ RUN mkdir $TGI_INSTALL_PREFIX && mkdir "$TGI_INSTALL_PREFIX/include" && mkdir "$TGI_INSTALL_PREFIX/lib" && \
CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --release --bin text-generation-backends-trtllm CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --release --bin text-generation-backends-trtllm
FROM nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04 as runtime FROM nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04 AS runtime
WORKDIR /usr/local/tgi/bin WORKDIR /usr/local/tgi/bin
ENV LD_LIBRARY_PATH="/usr/local/tgi/lib:/usr/local/tensorrt/lib:/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH" ENV LD_LIBRARY_PATH="/usr/local/tgi/lib:/usr/local/tensorrt/lib:/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH"