OpenLLM/.github/workflows/build.yml

name: Build and push OpenLLM base container
on:
  workflow_dispatch:
  push:
    branches:
      - 'main'
    tags:
      - '*'
    paths:
      - '.github/workflows/build-embedding.yml'
      - 'openllm-python/src/openllm/**'
      - 'openllm-core/src/openllm_core/**'
      - 'openllm-client/src/openllm_client/**'
  pull_request:
    branches:
      - 'main'
    paths:
      - '.github/workflows/build-embedding.yml'
      - 'openllm-python/src/openllm/**'
      - 'openllm-core/src/openllm_core/**'
      - 'openllm-client/src/openllm_client/**'
    types: [labeled, opened, synchronize, reopened]
env:
  LINES: 120
  COLUMNS: 120
  OPENLLM_DO_NOT_TRACK: True
  PYTHONUNBUFFERED: '1'
  AWS_REGION: us-west-2
concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
  cancel-in-progress: true
jobs:
  get_commit_message:
    name: Get commit message
    runs-on: ubuntu-latest
    if: "github.repository == 'bentoml/OpenLLM'" # Don't run on fork repository
    outputs:
      message: ${{ steps.commit_message.outputs.message }}
    steps:
      - uses: actions/checkout@3df4ab11eba7bda6032a0b82a6bb43b11571feac # ratchet:actions/checkout@v4
        # Gets the correct commit message for pull request
        with:
          ref: ${{ github.event.pull_request.head.sha }}
      - name: Get commit message
        id: commit_message
        run: |
          set -xe
          COMMIT_MSG=$(git log --no-merges -1 --oneline)
          echo "message=$COMMIT_MSG" >> $GITHUB_OUTPUT
          echo github.ref ${{ github.ref }}
  start-runner:
    name: Start self-hosted EC2 runner
    runs-on: ubuntu-latest
    needs: get_commit_message
    if: >-
      contains(needs.get_commit_message.outputs.message, '[ec2 build]') || github.event_name == 'workflow_dispatch' || (github.event_name == 'pull_request' && contains(github.event.pull_request.labels.*.name, '00 - EC2 Build')) || (github.event_name == 'push' && (startsWith(github.ref, 'refs/tags/v') || startsWith(github.ref, 'refs/heads/main')))
    env:
      EC2_INSTANCE_TYPE: t3.2xlarge
      EC2_AMI_ID: ami-089dafe9af191a0fd
      EC2_SUBNET_ID: subnet-0ca63188fe98788c1,subnet-05997205433b249d0,subnet-07ef5d3e974275fed,subnet-0161ef0151089bb0b
      EC2_SECURITY_GROUP: sg-051366641bf2b8049
    outputs:
      label: ${{ steps.start-ec2-runner.outputs.label }}
      ec2-instance-id: ${{ steps.start-ec2-runner.outputs.ec2-instance-id }}
    steps:
      - name: Configure AWS credentials
        uses: aws-actions/configure-aws-credentials@8c3f20df09ac63af7b3ae3d7c91f105f857d8497 # ratchet:aws-actions/configure-aws-credentials@v4.0.0
        with:
          aws-access-key-id: ${{ secrets.AWS_PROD_ACCESS_KEY_ID }}
          aws-secret-access-key: ${{ secrets.AWS_PROD_SECRET_ACCESS_KEY }}
          aws-region: ${{ env.AWS_REGION }}
      - name: Start EC2 Runner
        id: start-ec2-runner
        uses: aarnphm/ec2-github-runner@main # ratchet:exclude
        with:
          mode: start
          github-token: ${{ secrets.OPENLLM_PAT }}
          ec2-region: ${{ env.AWS_REGION }}
          ec2-image-id: ${{ env.EC2_AMI_ID }}
          ec2-instance-type: ${{ env.EC2_INSTANCE_TYPE }}
          subnet-id: ${{ env.EC2_SUBNET_ID }}
          security-group-id: ${{ env.EC2_SECURITY_GROUP }}
  build-and-push-image:
    name: Build and push OpenLLM base image
    concurrency:
      group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
      cancel-in-progress: true
    needs: start-runner
    runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
    permissions:
      contents: write
      packages: write
      # This is used to complete the identity challenge
      # with sigstore/fulcio when running outside of PRs.
      id-token: write
      security-events: write
    steps:
      - uses: actions/checkout@3df4ab11eba7bda6032a0b82a6bb43b11571feac # ratchet:actions/checkout@v4
        with:
          fetch-depth: 1
      - name: Inject slug/short variables
        uses: rlespinasse/github-slug-action@102b1a064a9b145e56556e22b18b19c624538d94 # ratchet:rlespinasse/github-slug-action@v4.4.1
      - name: Set up QEMU
        uses: docker/setup-qemu-action@68827325e0b33c7199eb31dd4e31fbe9023e06e3 # ratchet:docker/setup-qemu-action@v3.0.0
      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@f95db51fddba0c2d1ec667646a06c2ce06100226 # ratchet:docker/setup-buildx-action@v3.0.0
        with:
          install: true
          driver-opts: |
            image=moby/buildkit:master
            network=host
      - name: Install cosign
        if: github.event_name != 'pull_request'
        uses: sigstore/cosign-installer@11086d25041f77fe8fe7b9ea4e48e3b9192b8f19 # ratchet:sigstore/cosign-installer@v3.1.2
        with:
          cosign-release: 'v2.1.1'
      - name: Login to GitHub Container Registry
        uses: docker/login-action@343f7c4344506bcbf9b4de18042ae17996df046d # ratchet:docker/login-action@v3.0.0
        if: github.event_name != 'pull_request'
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}
      - name: Login to public ECR
        uses: docker/login-action@343f7c4344506bcbf9b4de18042ae17996df046d # ratchet:docker/login-action@v3.0.0
        with:
          registry: public.ecr.aws
          username: ${{ secrets.AWS_ACCESS_KEY_ID }}
          password: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
        env:
          AWS_REGION: us-east-1
      - name: Extract metadata tags and labels on PRs
        if: github.event_name == 'pull_request'
        id: meta-pr
        uses: docker/metadata-action@96383f45573cb7f253c731d3b3ab81c87ef81934 # ratchet:docker/metadata-action@v5.0.0
        with:
          images: |
            public.ecr.aws/y5w8i4y6/bentoml/openllm
          tags: |
            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}
          labels: |
            org.opencontainers.image.source="https://github.com/bentoml/OpenLLM"
      - name: Extract metadata tags and labels for main, release or tag
        if: github.event_name != 'pull_request'
        id: meta
        uses: docker/metadata-action@96383f45573cb7f253c731d3b3ab81c87ef81934 # ratchet:docker/metadata-action@v5.0.0
        with:
          flavor: |
            latest=auto
          images: |
            public.ecr.aws/y5w8i4y6/bentoml/openllm
            ghcr.io/bentoml/openllm
          tags: |
            type=semver,pattern={{version}}
            type=semver,pattern={{major}}.{{minor}}
            type=raw,value=latest,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}
          labels: |
            maintainer=aarnphm
            org.opencontainers.image.source="https://github.com/bentoml/OpenLLM"
      - name: Build and push Docker image
        id: build-and-push
        uses: docker/build-push-action@0565240e2d4ab88bba5387d719585280857ece09 # ratchet:docker/build-push-action@v5.0.0
        env:
          AWS_ACCESS_KEY_ID: ${{ secrets.AWS_PROD_ACCESS_KEY_ID }}
          AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_PROD_SECRET_ACCESS_KEY }}
        with:
          context: .
          file: openllm-python/src/openllm/bundle/oci/Dockerfile
          push: true
          platforms: 'linux/amd64'
          build-args: |
            GIT_SHA=${{ env.GITHUB_SHA }}
            DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}
          tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }}
          labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
          # TODO: Once https://github.com/aws/containers-roadmap/issues/876 is supported with OCI 1.1
          # then move back to saving cache within the public repo. For now we will save the cache manifest within our internal S3 buckets.
          # NOTE: the region of the S3 on prod is us-east-1, where the EC2 machine is at us-west-2
          cache-from: type=s3,region=us-east-1,bucket=openllm-cache,name=y5w8i4y6
          # @aarnphm: max is fine here, since we didn't do any custom code yet, so it is ok to cache every layer for optimal build time
          # We also ignore-error for now, just upload anything to the blob storage
          cache-to: type=s3,region=us-east-1,bucket=openllm-cache,name=y5w8i4y6,mode=max,compression=zstd,ignore-error=true
      - name: Sign the released image
        if: ${{ github.event_name != 'pull_request' }}
        env:
          COSIGN_EXPERIMENTAL: 'true'
        run: echo "${{ steps.meta.outputs.tags }}" | xargs -I {} cosign sign --yes {}@${{ steps.build-and-push.outputs.digest }}
      - name: Run Trivy in GitHub SBOM mode and submit results to Dependency Graph
        uses: aquasecurity/trivy-action@fbd16365eb88e12433951383f5e99bd901fc618f # ratchet:aquasecurity/trivy-action@master
        if: ${{ github.event_name != 'pull_request' }}
        with:
          image-ref: 'ghcr.io/bentoml/openllm:sha-${{ env.GITHUB_SHA_SHORT }}'
          format: 'github'
          output: 'dependency-results.sbom.json'
          github-pat: ${{ secrets.GITHUB_TOKEN }}
          scanners: 'vuln'
      - name: Run Trivy vulnerability scanner
        uses: aquasecurity/trivy-action@fbd16365eb88e12433951383f5e99bd901fc618f # ratchet:aquasecurity/trivy-action@master
        if: ${{ github.event_name != 'pull_request' }}
        with:
          image-ref: 'ghcr.io/bentoml/openllm:sha-${{ env.GITHUB_SHA_SHORT }}'
          format: 'sarif'
          output: 'trivy-results.sarif'
          severity: 'CRITICAL'
          scanners: 'vuln'
      - name: Upload Trivy scan results to GitHub Security tab
        uses: github/codeql-action/upload-sarif@00e563ead9f72a8461b24876bee2d0c2e8bd2ee8 # ratchet:github/codeql-action/upload-sarif@v2
        if: ${{ github.event_name != 'pull_request' }}
        with:
          sarif_file: 'trivy-results.sarif'
  # TODO: Add snapshot tests here.
  stop-runner:
    name: Stop self-hosted EC2 runner
    needs:
      - start-runner
      - build-and-push-image
      - get_commit_message
    runs-on: ubuntu-latest
    if: >-
      (contains(needs.get_commit_message.outputs.message, '[ec2 build]') || github.event_name == 'workflow_dispatch' || (github.event_name == 'pull_request' && contains(github.event.pull_request.labels.*.name, '00 - EC2 Build')) || (github.event_name == 'push' && (startsWith(github.ref, 'refs/tags/v') || startsWith(github.ref, 'refs/heads/main')))) && always()
    steps:
      - name: Configure AWS credentials
        uses: aws-actions/configure-aws-credentials@8c3f20df09ac63af7b3ae3d7c91f105f857d8497 # ratchet:aws-actions/configure-aws-credentials@v4.0.0
        with:
          aws-access-key-id: ${{ secrets.AWS_PROD_ACCESS_KEY_ID }}
          aws-secret-access-key: ${{ secrets.AWS_PROD_SECRET_ACCESS_KEY }}
          aws-region: ${{ env.AWS_REGION }}
      - name: Stop EC2 runner
        uses: aarnphm/ec2-github-runner@af796d217e24ecbbc5a2c49e780cd90616e2b962 # ratchet:aarnphm/ec2-github-runner@main
        with:
          mode: stop
          github-token: ${{ secrets.OPENLLM_PAT }}
          ec2-region: ${{ env.AWS_REGION }}
          label: ${{ needs.start-runner.outputs.label }}
          ec2-instance-id: ${{ needs.start-runner.outputs.ec2-instance-id }}