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 2024-05-02 15:39:43 +00:00
parent 52f593bba7
commit c70742654b
1 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
Dockerfile_amd
View File

@ -96,7 +96,6 @@ RUN pip uninstall -y triton && \
pip install .
RUN git clone --depth 1 --recursive --single-branch --branch 2.3-patched https://github.com/fxmarty/pytorch.git pytorch && cd pytorch && pip install -r requirements.txt --no-cache-dir
# RUN git clone --depth 1 --recursive --single-branch --branch release/2.3 https://github.com/pytorch/pytorch.git pytorch && cd pytorch && pip install -r requirements.txt --no-cache-dir
ARG _GLIBCXX_USE_CXX11_ABI="1"
ARG CMAKE_PREFIX_PATH="/opt/conda"
@ -116,6 +115,7 @@ ARG BUILD_CAFFE2="0" \
RUN cd pytorch && python tools/amd_build/build_amd.py && python setup.py install
# Set as recommended: https://github.com/ROCm/triton/wiki/A-script-to-set-program-execution-environment-in-ROCm
# Disabled for now as it is currently not stable with ROCm 6.1.
# ENV HIP_FORCE_DEV_KERNARG=1
FROM base AS kernel-builder
@ -184,8 +184,10 @@ COPY --from=exllamav2-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-31
COPY proto proto
COPY server server
COPY server/Makefile server/Makefile
# pip install -r requirements_rocm.txt && \
#pip install ".[accelerate, peft, outlines]" --no-cache-dir
RUN cd server && \
make gen-server && \
pip install -r requirements_rocm.txt && \
pip install ".[accelerate, peft, outlines]" --no-cache-dir
# Install benchmarker
COPY --from=builder /usr/src/target/release/text-generation-benchmark /usr/local/bin/text-generation-benchmark
@ -194,21 +196,19 @@ COPY --from=builder /usr/src/target/release/text-generation-router /usr/local/bi
# Install 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
# AWS Sagemaker compatible image
FROM base-copy as sagemaker
FROM base as sagemaker
COPY sagemaker-entrypoint.sh entrypoint.sh
RUN chmod +x entrypoint.sh
ENTRYPOINT ["./entrypoint.sh"]
# Final image
FROM base-copy
FROM base
# ENTRYPOINT ["text-generation-launcher"]
# CMD ["--json-output"]
COPY ./tgi-entrypoint.sh /tgi-entrypoint.sh
RUN chmod +x /tgi-entrypoint.sh
# NOTE: Temporarily, for TGI, please mount a volume and install locally the server with `cd /tgi/server && pip install ".[accelerate, peft, outlines]" --no-cache-dir`
ENTRYPOINT ["/tgi-entrypoint.sh"]
CMD ["--json-output"]