name: Build and push docker image to internal registry

on:
  workflow_dispatch:
  push:
    branches:
      - 'main'
    tags:
      - 'v*'
  pull_request:
    paths:
      - ".github/workflows/build.yaml"
      - "integration-tests/**"
      - "server/**"
      - "proto/**"
      - "router/**"
      - "launcher/**"
      - "Cargo.lock"
      - "rust-toolchain.toml"
      - "Dockerfile"
    branches:
      - 'main'

jobs:
  start-runner:
    name: Start self-hosted EC2 runner
    runs-on: ubuntu-latest
    env:
      AWS_REGION: us-east-1
      EC2_AMI_ID: ami-0789b6925c11b1fb2
      EC2_INSTANCE_TYPE: g5.12xlarge
      EC2_SUBNET_ID: subnet-931b34f5,subnet-ecb993cd,subnet-943dc2d8,subnet-45371f1a,subnet-ee93e0df,subnet-fddc3dfc
      EC2_SECURITY_GROUP: sg-030175c435ac141d6
    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@v1
        with:
          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
          aws-region: ${{ env.AWS_REGION }}
      - name: Start EC2 runner
        id: start-ec2-runner
        uses: philschmid/philschmid-ec2-github-runner@main
        with:
          mode: start
          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
          ec2-image-id: ${{ env.EC2_AMI_ID }}
          ec2-instance-type: ${{ env.EC2_INSTANCE_TYPE }}
          subnet-id: ${{ env.EC2_SUBNET_ID }}
          security-group-id: ${{ env.EC2_SECURITY_GROUP }}
          aws-resource-tags: > # optional, requires additional permissions
            [
              {"Key": "Name", "Value": "ec2-tgi-github-runner"},
              {"Key": "GitHubRepository", "Value": "${{ github.repository }}"}
            ]

  build-and-push-image:
    concurrency:
      group: ${{ github.workflow }}-build-and-push-image-${{ github.head_ref || github.run_id }}
      cancel-in-progress: true
    needs: start-runner # required to start the main job when the runner is ready
    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:
      - name: Checkout repository
        uses: actions/checkout@v3
      - name: Initialize Docker Buildx
        uses: docker/setup-buildx-action@v2.0.0
        with:
          install: true
      - name: Inject slug/short variables
        uses: rlespinasse/github-slug-action@v4.4.1
      - name: Tailscale
        uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966
        with:
          authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
      - name: Login to GitHub Container Registry
        if: github.event_name != 'pull_request'
        uses: docker/login-action@v2
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}
      - name: Login to internal Container Registry
        uses: docker/login-action@v2.1.0
        with:
          username: ${{ secrets.TAILSCALE_DOCKER_USERNAME }}
          password: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }}
          registry: registry.internal.huggingface.tech
      - name: Login to Azure Container Registry
        if: github.event_name != 'pull_request'
        uses: docker/login-action@v2.1.0
        with:
          username: ${{ secrets.AZURE_DOCKER_USERNAME }}
          password: ${{ secrets.AZURE_DOCKER_PASSWORD }}
          registry: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io
      # If pull request
      - name: Extract metadata (tags, labels) for Docker
        if: ${{ github.event_name == 'pull_request' }}
        id: meta-pr
        uses: docker/metadata-action@v4.3.0
        with:
          images: |
            registry.internal.huggingface.tech/api-inference/community/text-generation-inference
          tags: |
            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}
      # If main, release or tag
      - name: Extract metadata (tags, labels) for Docker
        if: ${{ github.event_name != 'pull_request' }}
        id: meta
        uses: docker/metadata-action@v4.3.0
        with:
          flavor: |
            latest=auto
          images: |
            registry.internal.huggingface.tech/api-inference/community/text-generation-inference
            ghcr.io/huggingface/text-generation-inference
            db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
          tags: |
            type=semver,pattern={{version}}
            type=semver,pattern={{major}}.{{minor}}
            type=raw,value=latest,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}
      - name: Build and push Docker image
        id: build-and-push
        uses: docker/build-push-action@v4
        with:
          context: .
          file: Dockerfile
          push: true
          platforms: 'linux/amd64'
          build-args: |
            GIT_SHA=${{ 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 }}
          cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache,mode=min
          cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache,mode=min

  integration-tests:
    concurrency:
      group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
      cancel-in-progress: true
    needs:
      - start-runner
      - build-and-push-image # Wait for the docker image to be built
    runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
    env:
      DOCKER_VOLUME: /cache
    steps:
      - uses: actions/checkout@v2
      - name: Inject slug/short variables
        uses: rlespinasse/github-slug-action@v4.4.1
      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: 3.9
      - name: Tailscale
        uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966
        with:
          authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
      - name: Prepare disks
        run: |
          sudo mkfs -t ext4 /dev/nvme1n1
          sudo mkdir ${{ env.DOCKER_VOLUME }}
          sudo mount /dev/nvme1n1 ${{ env.DOCKER_VOLUME }}
      - name: Install
        run: |
          make install-integration-tests
      - name: Run tests
        run: |
          export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT }}
          export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }}
          pytest -s -vv integration-tests

  build-and-push-image-rocm:
    concurrency:
      group: ${{ github.workflow }}-build-and-push-image-rocm-${{ github.head_ref || github.run_id }}
      cancel-in-progress: true
    needs:
      - start-runner
      - build-and-push-image # Wait for the main docker image to be built
      - integration-tests # Wait for the main integration-tests
    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:
      - name: Checkout repository
        uses: actions/checkout@v3
      - name: Initialize Docker Buildx
        uses: docker/setup-buildx-action@v2.0.0
        with:
          install: true
      - name: Inject slug/short variables
        uses: rlespinasse/github-slug-action@v4.4.1
      - name: Tailscale
        uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966
        with:
          authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
      - name: Login to GitHub Container Registry
        if: github.event_name != 'pull_request'
        uses: docker/login-action@v2
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}
      - name: Login to internal Container Registry
        uses: docker/login-action@v2.1.0
        with:
          username: ${{ secrets.TAILSCALE_DOCKER_USERNAME }}
          password: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }}
          registry: registry.internal.huggingface.tech
      - name: Login to Azure Container Registry
        if: github.event_name != 'pull_request'
        uses: docker/login-action@v2.1.0
        with:
          username: ${{ secrets.AZURE_DOCKER_USERNAME }}
          password: ${{ secrets.AZURE_DOCKER_PASSWORD }}
          registry: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io
      # If pull request
      - name: Extract metadata (tags, labels) for Docker
        if: ${{ github.event_name == 'pull_request' }}
        id: meta-pr
        uses: docker/metadata-action@v4.3.0
        with:
          images: |
            registry.internal.huggingface.tech/api-inference/community/text-generation-inference
          tags: |
            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-rocm
      # If main, release or tag
      - name: Extract metadata (tags, labels) for Docker
        if: ${{ github.event_name != 'pull_request' }}
        id: meta
        uses: docker/metadata-action@v4.3.0
        with:
          flavor: |
            latest=false
          images: |
            registry.internal.huggingface.tech/api-inference/community/text-generation-inference
            ghcr.io/huggingface/text-generation-inference
            db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
          tags: |
            type=semver,pattern={{version}}-rocm
            type=semver,pattern={{major}}.{{minor}}-rocm
            type=raw,value=latest-rocm,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-rocm
      - name: Build and push Docker image
        id: build-and-push
        uses: docker/build-push-action@v4
        with:
          context: .
          file: Dockerfile_amd
          push: true
          platforms: 'linux/amd64'
          build-args: |
            GIT_SHA=${{ env.GITHUB_SHA }}
            DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}-rocm
          tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }}
          labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
          cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-rocm,mode=min
          cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-rocm,mode=min

  build-and-push-image-intel:
    concurrency:
      group: ${{ github.workflow }}-build-and-push-image-intel-${{ github.head_ref || github.run_id }}
      cancel-in-progress: true
    needs:
      - start-runner
      - build-and-push-image # Wait for the main docker image to be built
      - integration-tests # Wait for the main integration-tests
    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
    outputs:
      # env is not available in the later `container:`, but previous job outputs are.
      short_sha: ${{ env.GITHUB_SHA_SHORT }}
    steps:
      - name: Checkout repository
        uses: actions/checkout@v3
      - name: Initialize Docker Buildx
        uses: docker/setup-buildx-action@v2.0.0
        with:
          install: true
      - name: Inject slug/short variables
        uses: rlespinasse/github-slug-action@v4.4.1
      - name: Tailscale
        uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966
        with:
          authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
      - name: Login to GitHub Container Registry
        if: github.event_name != 'pull_request'
        uses: docker/login-action@v2
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}
      - name: Login to internal Container Registry
        uses: docker/login-action@v2.1.0
        with:
          username: ${{ secrets.TAILSCALE_DOCKER_USERNAME }}
          password: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }}
          registry: registry.internal.huggingface.tech
      - name: Login to Azure Container Registry
        if: github.event_name != 'pull_request'
        uses: docker/login-action@v2.1.0
        with:
          username: ${{ secrets.AZURE_DOCKER_USERNAME }}
          password: ${{ secrets.AZURE_DOCKER_PASSWORD }}
          registry: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io
      # If pull request
      - name: Extract metadata (tags, labels) for Docker
        if: ${{ github.event_name == 'pull_request' }}
        id: meta-pr
        uses: docker/metadata-action@v4.3.0
        with:
          images: |
            registry.internal.huggingface.tech/api-inference/community/text-generation-inference
          tags: |
            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-intel
      # If main, release or tag
      - name: Extract metadata (tags, labels) for Docker
        if: ${{ github.event_name != 'pull_request' }}
        id: meta
        uses: docker/metadata-action@v4.3.0
        with:
          flavor: |
            latest=false
          images: |
            registry.internal.huggingface.tech/api-inference/community/text-generation-inference
            ghcr.io/huggingface/text-generation-inference
            db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
          tags: |
            type=semver,pattern={{version}}-intel
            type=semver,pattern={{major}}.{{minor}}-intel
            type=raw,value=latest-intel,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-intel
      - name: Build and push Docker image
        id: build-and-push
        uses: docker/build-push-action@v4
        with:
          context: .
          file: Dockerfile_intel
          push: true
          platforms: 'linux/amd64'
          build-args: |
            GIT_SHA=${{ env.GITHUB_SHA }}
            DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}-intel
          tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }}
          labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
          cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-intel,mode=min
          cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-intel,mode=min

  stop-runner:
    name: Stop self-hosted EC2 runner
    needs:
      - start-runner
      - build-and-push-image
      - build-and-push-image-rocm
      - build-and-push-image-intel
      - integration-tests
    runs-on: ubuntu-latest
    env:
      AWS_REGION: us-east-1
    if: ${{ always() }} # required to stop the runner even if the error happened in the previous jobs
    steps:
      - name: Configure AWS credentials
        uses: aws-actions/configure-aws-credentials@v1
        with:
          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
          aws-region: ${{ env.AWS_REGION }}
      - name: Stop EC2 runner
        uses: philschmid/philschmid-ec2-github-runner@main
        with:
          mode: stop
          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
          label: ${{ needs.start-runner.outputs.label }}
          ec2-instance-id: ${{ needs.start-runner.outputs.ec2-instance-id }}

  # TODO: Move this to `build_amd.yml` (and `build_nvidia.yml`)

  # integration-tests-rocm:
  #   concurrency:
  #     group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
  #     cancel-in-progress: true
  #   needs:
  #     - start-runner
  #     - build-and-push-image
  #     - integration-tests
  #     - build-and-push-image-rocm
  #     - stop-runner
  #   runs-on: [self-hosted, amd-gpu, multi-gpu, mi300]
  #   container:
  #     image: registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ needs.build-and-push-image-rocm.outputs.short_sha }}-rocm
  #     options: --device /dev/kfd --device /dev/dri --env ROCR_VISIBLE_DEVICES --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/cache
  #   env:
  #     DOCKER_VOLUME: /cache
  #   steps:
  #     - name: ROCM-SMI
  #       run: |
  #         rocm-smi
  #     - name: ROCM-INFO
  #       run: |
  #         rocminfo  | grep "Agent" -A 14
  #     - name: Show ROCR environment
  #       run: |
  #         echo "ROCR: $ROCR_VISIBLE_DEVICES"
  #     - name: Install
  #       run: |
  #         make install-integration-tests
  #     - name: Run tests
  #       run: |
  #         export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }}
  #         pytest -s -vv integration-tests