diff --git a/.github/workflows/post-merge-container-update.yml b/.github/workflows/post-merge-container-update.yml new file mode 100644 index 000000000..9fd8239e7 --- /dev/null +++ b/.github/workflows/post-merge-container-update.yml @@ -0,0 +1,112 @@ +name: Post-merge container update + +# This workflow uses actions that are not certified by GitHub. +# They are provided by a third-party and are governed by +# separate terms of service, privacy policy, and support +# documentation. + +on: + push: + branches: [ "main" ] + paths: ['tripy/Dockerfile', 'tripy/pyproject.toml'] + # TODO: For testing purposes - remove before merging + pull_request: + +env: + # Use docker.io for Docker Hub if empty + REGISTRY: ghcr.io + # github.repository as / + IMAGE_NAME: ${{ github.repository }} + + +jobs: + build: + + runs-on: ubuntu-latest + permissions: + contents: read + packages: write + # This is used to complete the identity challenge + # with sigstore/fulcio when running outside of PRs. + id-token: write + + steps: + # Based on https://stackoverflow.com/q/75536771 + - name: Free disk space + run: | + sudo docker system prune -a -f + sudo rm -rf \ + /usr/share/dotnet "$AGENT_TOOLSDIRECTORY" /usr/local/lib/android /opt/ghc \ + /usr/local/share/powershell /usr/share/swift /usr/local/.ghcup \ + /usr/lib/jvm + + sudo apt-get purge microsoft-edge-stable || true + sudo apt-get purge google-cloud-cli || true + sudo apt-get purge dotnet-sdk-* || true + sudo apt-get purge google-chrome-stable || true + + sudo apt-get autoremove -y + sudo apt-get autoclean -y + + - name: Show disk usage + run: df . -h + + - name: Checkout repository + uses: actions/checkout@v4 + + # Install the cosign tool + # https://github.com/sigstore/cosign-installer + - name: Install cosign + uses: sigstore/cosign-installer@59acb6260d9c0ba8f4a2f9d9b48431a222b68e20 #v3.5.0 + with: + cosign-release: 'v2.2.4' + + # Set up BuildKit Docker container builder to be able to build + # multi-platform images and export cache + # https://github.com/docker/setup-buildx-action + - name: Set up Docker Buildx + uses: docker/setup-buildx-action@f95db51fddba0c2d1ec667646a06c2ce06100226 # v3.0.0 + + # Login against a Docker registry + # https://github.com/docker/login-action + - name: Log into registry ${{ env.REGISTRY }} + uses: docker/login-action@343f7c4344506bcbf9b4de18042ae17996df046d # v3.0.0 + with: + registry: ${{ env.REGISTRY }} + username: ${{ github.actor }} + password: ${{ secrets.GITHUB_TOKEN }} + + # Extract metadata (tags, labels) for Docker + # https://github.com/docker/metadata-action + - name: Extract Docker metadata + id: meta + uses: docker/metadata-action@96383f45573cb7f253c731d3b3ab81c87ef81934 # v5.0.0 + with: + images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }} + + # Build and push Docker image with Buildx + # https://github.com/docker/build-push-action + - name: Build and push Docker image + id: build-and-push + uses: docker/build-push-action@0565240e2d4ab88bba5387d719585280857ece09 # v5.0.0 + with: + context: tripy/ + push: true + tags: ${{ steps.meta.outputs.tags }}/tripy:latest + labels: ${{ steps.meta.outputs.labels }} + cache-from: type=gha + cache-to: type=gha,mode=max + + # Sign the resulting Docker image digest. + # This will only write to the public Rekor transparency log when the Docker + # repository is public to avoid leaking data. If you would like to publish + # transparency data even for private images, pass --force to cosign below. + # https://github.com/sigstore/cosign + - name: Sign the published Docker image + env: + # https://docs.github.com/en/actions/security-guides/security-hardening-for-github-actions#using-an-intermediate-environment-variable + TAGS: tripy + DIGEST: ${{ steps.build-and-push.outputs.digest }} + # This step uses the identity token to provision an ephemeral certificate + # against the sigstore community Fulcio instance. + run: echo "${TAGS}" | xargs -I {} cosign sign --yes {}@${DIGEST} diff --git a/tripy/Dockerfile b/tripy/Dockerfile index 242ddd337..9fcaf3a41 100644 --- a/tripy/Dockerfile +++ b/tripy/Dockerfile @@ -10,13 +10,14 @@ ENV DEBIAN_FRONTEND=noninteractive ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64/:/usr/local/cuda/targets/x86_64-linux/lib/:/usr/lib/x86_64-linux-gnu/:$LD_LIBRARY_PATH +# MPI is currently required for MLIR-TRT RUN groupadd -r -f -g ${gid} trtuser && \ useradd -o -r -l -u ${uid} -g ${gid} -ms /bin/bash trtuser && \ usermod -aG sudo trtuser && \ echo 'trtuser:nvidia' | chpasswd && \ mkdir -p /workspace && chown trtuser /workspace && \ apt-get update && \ - apt-get install -y software-properties-common sudo fakeroot python3-pip gdb git wget libcudnn8 curl jq && \ + apt-get install -y software-properties-common sudo fakeroot python3-pip gdb git wget libcudnn8 curl jq libopenmpi3 libopenmpi-dev && \ apt-get clean && \ python3 -m pip install --upgrade pip @@ -25,9 +26,10 @@ COPY .lldbinit /root/ # Install the recommended version of TensorRT for development. RUN cd /usr/lib/ && \ - wget https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.1.0/tars/TensorRT-10.1.0.27.Linux.x86_64-gnu.cuda-12.4.tar.gz && \ - tar -xvzf TensorRT-10.1.0.27.Linux.x86_64-gnu.cuda-12.4.tar.gz && \ - rm TensorRT-10.1.0.27.Linux.x86_64-gnu.cuda-12.4.tar.gz + wget -q https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/10.1.0/tars/TensorRT-10.1.0.27.Linux.x86_64-gnu.cuda-12.4.tar.gz && \ + tar -xzf TensorRT-10.1.0.27.Linux.x86_64-gnu.cuda-12.4.tar.gz && \ + rm TensorRT-10.1.0.27.Linux.x86_64-gnu.cuda-12.4.tar.gz && \ + rm -rf /usr/lib/TensorRT-10.1.0.27/data/ /usr/lib/TensorRT-10.1.0.27/doc/ /usr/lib/TensorRT-10.1.0.27/samples /usr/lib/TensorRT-10.1.0.27/bin /usr/lib/TensorRT-10.1.0.27/python ENV LD_LIBRARY_PATH=/usr/lib/TensorRT-10.1.0.27/lib/:$LD_LIBRARY_PATH COPY pyproject.toml /tripy/pyproject.toml @@ -42,8 +44,6 @@ RUN pip install .[docs,dev,test] \ # Configure mlir-tensorrt packages ######################################## -RUN apt-get install -y libopenmpi3 libopenmpi-dev - # Installl lldb for debugging purposes in Tripy container. # The LLVM version should correspond on LLVM_VERSION specified in https://github.com/NVIDIA/TensorRT-Incubator/blob/main/mlir-tensorrt/build_tools/docker/Dockerfile#L30. ARG LLVM_VERSION=17