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

misc(ci): provide mecanism to cache inside container

This commit is contained in:
Morgan Funtowicz 2024-12-12 12:45:14 +01:00
parent e703c84578
commit 5910dabb4e
2 changed files with 21 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
.github/workflows/build_trtllm.yaml vendored
View File

@ -38,6 +38,7 @@ jobs:
override: true override: true
- name: "Configure AWS Credentials" - name: "Configure AWS Credentials"
id: aws-creds
uses: aws-actions/configure-aws-credentials@v4 uses: aws-actions/configure-aws-credentials@v4
with: with:
aws-region: us-east-1 aws-region: us-east-1
@ -59,12 +60,14 @@ jobs:
push: false push: false
platforms: 'linux/amd64' platforms: 'linux/amd64'
build-args: | build-args: |
AWS_ACCESS_KEY_ID: ${{ steps.aws-creds.outputs.aws-access-key-id }}
AWS_SECRET_ACCESS_KEY: ${{ steps.aws-creds.outputs.aws-secret-access-key }}
BUILD_TYPE=debug BUILD_TYPE=debug
SCCACHE_BUCKET: ${{ secrets.AWS_S3_BUCKET_GITHUB_TGI_TEST }} SCCACHE_BUCKET: ${{ secrets.AWS_S3_BUCKET_GITHUB_TGI_TEST }}
SCCACHE_REGION: "us-east-1" SCCACHE_REGION: us-east-1
SCCACHE_S3_USE_SSL: false SCCACHE_S3_USE_SSL: false
SCCACHE_S3_KEY_PREFIX: "tgi+trtllm" SCCACHE_S3_KEY_PREFIX: trtllm
RUSTC_WRAPPER: sccache

16
Dockerfile_trtllm
View File

@ -2,6 +2,13 @@ ARG CUDA_ARCH_LIST="75-real;80-real;86-real;89-real;90-real"
ARG OMPI_VERSION="4.1.7rc1" ARG OMPI_VERSION="4.1.7rc1"
ARG BUILD_TYPE=release ARG BUILD_TYPE=release
# Additional arguments if we enable sccache in the CI/CD
ARG AWS_ACCESS_KEY_ID
ARG AWS_SECRET_ACCESS_KEY
ARG SCCACHE_BUCKET=""
ARG SCCACHE_REGION=""
ARG SCCACHE_S3_KEY_PREFIX=""
# CUDA dependent dependencies resolver stage # CUDA dependent dependencies resolver stage
FROM nvidia/cuda:12.6.3-cudnn-devel-ubuntu24.04 AS cuda-builder FROM nvidia/cuda:12.6.3-cudnn-devel-ubuntu24.04 AS cuda-builder
@ -68,11 +75,18 @@ ENV CMAKE_PREFIX_PATH="/usr/local/mpi:/usr/local/tensorrt:$CMAKE_PREFIX_PATH"
ENV LD_LIBRARY_PATH="/usr/local/mpi/lib:$LD_LIBRARY_PATH" ENV LD_LIBRARY_PATH="/usr/local/mpi/lib:$LD_LIBRARY_PATH"
ENV PKG_CONFIG_PATH="/usr/local/mpi/lib/pkgconfig:$PKG_CONFIG_PATH" ENV PKG_CONFIG_PATH="/usr/local/mpi/lib/pkgconfig:$PKG_CONFIG_PATH"
# Retrieve potential build arg for S3 caching
ENV AWS_ACCESS_KEY_ID ${AWS_ACCESS_KEY_ID}
ENV AWS_SECRET_ACCESS_KEY ${AWS_SECRET_ACCESS_KEY}
ENV SCCACHE_BUCKET ${SCCACHE_BUCKET}
ENV SCCACHE_REGION ${SCCACHE_REGION}
ENV SCCACHE_S3_KEY_PREFIX ${SCCACHE_S3_KEY_PREFIX}
COPY . . COPY . .
COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt COPY --from=trt-builder /usr/local/tensorrt /usr/local/tensorrt
COPY --from=mpi-builder /usr/local/mpi /usr/local/mpi 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" && \ RUN mkdir $TGI_INSTALL_PREFIX && mkdir "$TGI_INSTALL_PREFIX/include" && mkdir "$TGI_INSTALL_PREFIX/lib" && \
CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX sccache build --${BUILD_TYPE} --package text-generation-backends-trtllm --bin text-generation-backends-trtllm CMAKE_INSTALL_PREFIX=$TGI_INSTALL_PREFIX cargo build --${BUILD_TYPE} --package text-generation-backends-trtllm --bin text-generation-backends-trtllm
FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04 AS runtime 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 && \ RUN apt update && apt install -y libucx0 pipx python3-minimal python3-dev python3-pip python3-venv && \