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

chore(trtllm): disable tokenizer parallelism by default

This commit is contained in:
Morgan Funtowicz 2024-10-21 09:25:31 +02:00
parent 62f33d7ecd
commit e3bce407be
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
Dockerfile_trtllm
View File

@ -86,6 +86,7 @@ FROM nvidia/cuda:12.6.1-cudnn-runtime-ubuntu22.04 AS runtime
WORKDIR /usr/local/tgi/bin WORKDIR /usr/local/tgi/bin
ENV LD_LIBRARY_PATH="/usr/local/tgi/lib:/usr/local/tensorrt/lib:/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH" ENV LD_LIBRARY_PATH="/usr/local/tgi/lib:/usr/local/tensorrt/lib:/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH"
ENV TOKENIZERS_PARALLELISM=false
ENV OMPI_MCA_plm_rsh_agent="" ENV OMPI_MCA_plm_rsh_agent=""
COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi