huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-06-19 15:52:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Applying to other builds.

Browse Source
This commit is contained in:
Nicolas Patry 2025-02-06 09:46:25 +01:00
parent a3b05fc943
commit 8a3c9fb79a
No known key found for this signature in database
GPG Key ID: D2920555C90F704C
3 changed files with 23 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Dockerfile
View File

@ -208,7 +208,7 @@ COPY server/Makefile server/Makefile
ENV UV_SYSTEM_PYTHON=1 ENV UV_SYSTEM_PYTHON=1
RUN cd server && \ RUN cd server && \
pip install -U pip uv && \ pip install -U pip uv && \
uv sync --frozen --extra gen --extra attention --extra bnb --extra accelerate --extra compressed-tensors --extra marlin --extra moe --extra quantize --extra peft --extra outlines && \ uv sync --frozen --extra gen --extra attention --extra bnb --extra accelerate --extra compressed-tensors --extra marlin --extra moe --extra quantize --extra peft --extra outlines --no-install-project && \
. ./.venv/bin/activate && \ . ./.venv/bin/activate && \
make gen-server-raw make gen-server-raw

11
Dockerfile_amd
View File

@ -320,9 +320,16 @@ COPY server server
COPY server/Makefile server/Makefile COPY server/Makefile server/Makefile
ENV UV_SYSTEM_PYTHON=1 ENV UV_SYSTEM_PYTHON=1
RUN cd server && \ RUN cd server && \
make gen-server && \
pip install -U pip uv && \ pip install -U pip uv && \
uv pip install -r requirements_rocm.txt --no-cache-dir uv sync --frozen --extra gen --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines --no-install-project && \
. ./.venv/bin/activate && \
make gen-server-raw
RUN cd server && \
uv sync --frozen --extra gen --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines && \
. ./.venv/bin/activate && \
pwd && \
text-generation-server --help
# Install benchmarker # Install benchmarker
COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark

16
Dockerfile_intel
View File

@ -215,9 +215,16 @@ COPY server server
COPY server/Makefile server/Makefile COPY server/Makefile server/Makefile
ENV UV_SYSTEM_PYTHON=1 ENV UV_SYSTEM_PYTHON=1
RUN cd server && \ RUN cd server && \
make gen-server && \
pip install -U pip uv && \ pip install -U pip uv && \
uv pip install -e ".[accelerate, compressed-tensors, peft, outlines]" --no-cache-dir uv sync --frozen --extra gen --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines --no-install-project && \
. ./.venv/bin/activate && \
make gen-server-raw
RUN cd server && \
uv sync --frozen --extra gen --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines && \
. ./.venv/bin/activate && \
pwd && \
text-generation-server --help
# Install benchmarker # Install benchmarker
COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark
@ -231,5 +238,8 @@ ENV ATTENTION=flashdecoding-ipex
ENV PREFIX_CACHING=1 ENV PREFIX_CACHING=1
ENV PREFILL_CHUNKING=1 ENV PREFILL_CHUNKING=1
ENV CUDA_GRAPHS=0 ENV CUDA_GRAPHS=0
ENTRYPOINT ["text-generation-launcher"] COPY ./tgi-entrypoint.sh /tgi-entrypoint.sh
RUN chmod +x /tgi-entrypoint.sh
ENTRYPOINT ["/tgi-entrypoint.sh"]
CMD ["--json-output"] CMD ["--json-output"]