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

The good old monkey.

Browse Source
This commit is contained in:
Nicolas Patry 2025-02-05 16:53:36 +01:00
parent 830c25dd5a
commit 19ea893956
No known key found for this signature in database
GPG Key ID: D2920555C90F704C
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
Dockerfile
View File

@ -232,12 +232,14 @@ COPY server server
COPY server/Makefile server/Makefile
ENV UV_SYSTEM_PYTHON=1
RUN cd server && \
make gen-server && \
# make gen-server && \
pip install -U pip uv && \
uv pip install -r requirements_cuda.txt
# uv pip install -r requirements_cuda.txt
uv sync --frozen --extra attention --extra bnb --extra accelerate --extra compressed-tensors --extra marlin --extra moe --extra quantize --extra peft --extra outlines && \
mv ./.venv/lib/python3.11/site-packages/* /opt/conda/lib/python3.11/site-packages/
# uv pip install nvidia-nccl-cu12==2.22.3
ENV LD_PRELOAD=/opt/conda/lib/python3.11/site-packages/nvidia/nccl/lib/libnccl.so.2
# ENV LD_PRELOAD=/opt/conda/lib/python3.11/site-packages/nvidia/nccl/lib/libnccl.so.2
# Required to find libpython within the rust binaries
ENV LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/opt/conda/lib/"
# This is needed because exl2 tries to load flash-attn