huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

misc(backend): again

Browse Source
This commit is contained in:
Morgan Funtowicz 2024-12-20 14:20:41 +01:00
parent 90bc54486a
commit 038361796b
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
Dockerfile_trtllm
View File

@ -112,7 +112,8 @@ COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi
RUN mkdir $TGI_INSTALL_PREFIX && mkdir "$TGI_INSTALL_PREFIX/include" && mkdir "$TGI_INSTALL_PREFIX/lib" && \
python3 backends/trtllm/scripts/setup_sccache.py --is-gha-build $IS_GHA_BUILD -k $AWS_ACCESS_KEY_ID -s $AWS_SECRET_KEY_ID -t $AWS_SESSION_TOKEN -b $SCCACHE_BUCKET -r $SSCACHE_REGION -p $SCCACHE_S3_KEY_PREFIX && \
RUSTC_WRAPPER=sccache CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --profile ${build_type} --package text-generation-backends-trtllm --bin text-generation-backends-trtllm
RUSTC_WRAPPER=sccache CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --profile ${build_type} --package text-generation-backends-trtllm --bin text-generation-backends-trtllm && \
sccache --show-stats
FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04 AS runtime
RUN apt update && apt install -y libucx0 pipx python3-minimal python3-dev python3-pip python3-venv && \