huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

misc(backend): again

Browse Source
This commit is contained in:
Morgan Funtowicz 2024-12-20 12:27:28 +01:00
parent 34f435d83d
commit d0c0a3c523
1 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
Dockerfile_trtllm
View File

@ -78,6 +78,13 @@ ARG sccache_bucket
ARG sccache_s3_key_prefix
ARG sscache_region
ENV AWS_ACCESS_KEY_ID=$aws_access_key_id
ENV AWS_SECRET_KEY_ID=$aws_secret_key_id
ENV AWS_SESSION_TOKEN=$aws_session_token
ENV SCCACHE_BUCKET=$sccache_bucket
ENV SCCACHE_S3_KEY_PREFIX=$SCCACHE_S3_KEY_PREFIX
ENV SSCACHE_REGION=$sscache_region
ENV CMAKE_PREFIX_PATH="/usr/local/mpi:/usr/local/tensorrt:$CMAKE_PREFIX_PATH"
ENV CUDA_ARCH_LIST=${cuda_arch_list}
ENV IS_GHA_BUILD ${is_gha_build}
@ -89,7 +96,7 @@ COPY . .
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 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 } && \
python3 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
FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04 AS runtime