cloudbuild.yaml

steps:
# Build the container image
- name: 'gcr.io/cloud-builders/docker'
  args: ['build', '-t', 'us-east1-docker.pkg.dev/$PROJECT_ID/cloud-run-source-deploy/marker-gpu-api:latest', '-f', 'Dockerfile.gpu', '.']

# Push the container image to Container Registry
- name: 'gcr.io/cloud-builders/docker'
  args: ['push', 'us-east1-docker.pkg.dev/$PROJECT_ID/cloud-run-source-deploy/marker-gpu-api:latest']

# Create a Compute Engine instance with GPU
- name: 'gcr.io/cloud-builders/gcloud'
  entrypoint: 'bash'
  args:
  - '-c'
  - |
    gcloud compute instances create marker-gpu-instance \
      --project=$PROJECT_ID \
      --zone=us-east1-b \
      --machine-type=n1-standard-4 \
      --network-interface=network-tier=PREMIUM,subnet=default \
      --maintenance-policy=TERMINATE \
      --provisioning-model=STANDARD \
      --service-account=795058584669-compute@developer.gserviceaccount.com \
      --scopes=https://www.googleapis.com/auth/cloud-platform \
      --accelerator=count=1,type=nvidia-tesla-t4 \
      --tags=http-server,https-server \
      --create-disk=auto-delete=yes,boot=yes,device-name=marker-gpu-instance,image=projects/cos-cloud/global/images/cos-stable-109-17800-147-15,mode=rw,size=50,type=pd-balanced \
      --no-shielded-secure-boot \
      --shielded-vtpm \
      --shielded-integrity-monitoring \
      --reservation-affinity=any \
      --metadata=startup-script="#! /bin/bash
    # Install NVIDIA drivers
    cos-extensions install gpu
    mount -o remount,exec /var/lib/nvidia
    /var/lib/nvidia/bin/nvidia-smi

    # Pull and run the marker-api container
    docker pull us-east1-docker.pkg.dev/$PROJECT_ID/cloud-run-source-deploy/marker-gpu-api:latest
    docker run -d --gpus all -p 80:8080 \
      -e PORT=8080 \
      -e GOOGLE_CLOUD_PROJECT=$PROJECT_ID \
      us-east1-docker.pkg.dev/$PROJECT_ID/cloud-run-source-deploy/marker-gpu-api:latest
    "

# Create firewall rule to allow HTTP traffic
- name: 'gcr.io/cloud-builders/gcloud'
  entrypoint: 'bash'
  args:
  - '-c'
  - |
    gcloud compute firewall-rules create allow-http \
      --direction=INGRESS \
      --priority=1000 \
      --network=default \
      --action=ALLOW \
      --rules=tcp:80 \
      --source-ranges=0.0.0.0/0 \
      --target-tags=http-server || echo "Firewall rule already exists"

# No substitutions needed as we're using PROJECT_ID directly

options:
  logging: CLOUD_LOGGING_ONLY