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

correctly setup linking search path for runtime layer

This commit is contained in:
Morgan Funtowicz 2024-07-22 14:42:43 +00:00
parent fd06ca6e7e
commit a32ef3b875
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
backends/trtllm/Dockerfile
View File

@ -51,7 +51,12 @@ RUN mkdir /usr/local/tgi && mkdir /usr/local/tgi/include && mkdir /usr/local/tgi
cargo build --release --bin text-generation-backends-trtllm
FROM nvcr.io/nvidia/pytorch:24.05-py3
WORKDIR /opt
WORKDIR /usr/local/tgi/bin
ENV LD_LIBRARY_PATH="usr/local/tgi/lib:$LD_LIBRARY_PATH"
RUN ln -s /usr/local/cuda/lib64/stubs/libcuda.so /usr/local/cuda/lib64/stubs/libcuda.so.1 && \
ln -s /usr/local/cuda/lib64/stubs/libnvidia-ml.so /usr/local/cuda/lib64/stubs/libnvidia-ml.so.1
COPY --from=cuda-builder /usr/local/tensorrt /usr/local/tensorrt
COPY --from=cuda-builder /usr/local/tgi /usr/local/tgi