huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

cleanup dockerfile

Browse Source
This commit is contained in:
fxmarty 2024-05-17 09:15:11 +00:00
parent 2a7ba6ee9c
commit eea3226780
1 changed files with 9 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
Dockerfile_amd
View File

@ -36,7 +36,7 @@ COPY launcher launcher
RUN cargo build --release RUN cargo build --release
# Text Generation Inference base image for RoCm # Text Generation Inference base image for RoCm
FROM rocm/dev-ubuntu-22.04:6.1 as base FROM rocm/dev-ubuntu-22.04:6.1.1_hip_update as base
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
build-essential \ build-essential \
@ -114,13 +114,6 @@ ARG BUILD_CAFFE2="0" \
RUN cd pytorch && python tools/amd_build/build_amd.py && python setup.py install RUN cd pytorch && python tools/amd_build/build_amd.py && python setup.py install
ARG GITHUB_TOKEN
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends wget && \
rm -rf /var/lib/apt/lists/* && \
wget --header "Authorization: token ${GITHUB_TOKEN}" https://raw.githubusercontent.com/fxmarty/patched_hipruntime/main/libamdhip64.so.6
ENV LD_PRELOAD="/libamdhip64.so.6"
# Set as recommended: https://github.com/ROCm/triton/wiki/A-script-to-set-program-execution-environment-in-ROCm # Set as recommended: https://github.com/ROCm/triton/wiki/A-script-to-set-program-execution-environment-in-ROCm
ENV HIP_FORCE_DEV_KERNARG=1 ENV HIP_FORCE_DEV_KERNARG=1
@ -193,6 +186,10 @@ COPY --from=exllamav2-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-31
COPY proto proto COPY proto proto
COPY server server COPY server server
COPY server/Makefile server/Makefile COPY server/Makefile server/Makefile
RUN cd server && \
make gen-server && \
pip install -r requirements_rocm.txt && \
pip install ".[accelerate, peft, outlines]" --no-cache-dir
# Install benchmarker # Install benchmarker
COPY --from=builder /usr/src/target/release/text-generation-benchmark /usr/local/bin/text-generation-benchmark COPY --from=builder /usr/src/target/release/text-generation-benchmark /usr/local/bin/text-generation-benchmark
@ -201,11 +198,6 @@ COPY --from=builder /usr/src/target/release/text-generation-router /usr/local/bi
# Install launcher # Install launcher
COPY --from=builder /usr/src/target/release/text-generation-launcher /usr/local/bin/text-generation-launcher COPY --from=builder /usr/src/target/release/text-generation-launcher /usr/local/bin/text-generation-launcher
RUN cd server && \
make gen-server && \
pip install -r requirements_rocm.txt
#pip install ".[accelerate, peft, outlines]" --no-cache-dir
# AWS Sagemaker compatible image # AWS Sagemaker compatible image
FROM base as sagemaker FROM base as sagemaker
@ -217,8 +209,8 @@ ENTRYPOINT ["./entrypoint.sh"]
# Final image # Final image
FROM base-copy FROM base-copy
# COPY ./tgi-entrypoint.sh /tgi-entrypoint.sh COPY ./tgi-entrypoint.sh /tgi-entrypoint.sh
# RUN chmod +x /tgi-entrypoint.sh RUN chmod +x /tgi-entrypoint.sh
# ENTRYPOINT ["/tgi-entrypoint.sh"] ENTRYPOINT ["/tgi-entrypoint.sh"]
# CMD ["--json-output"] CMD ["--json-output"]