Current Environment: GOOGLE_CLOUD_PROJECT=aisprint-491218 GOOGLE_CLOUD_LOCATION=us-east4 SERVICE_NAME=gpu-2b-l4-devops-agent MODEL_NAME=/mnt/models/gemma-4-E2B-it VLLM_BASE_URL= Cloud Run here is --no-allow-unauthenticated. If calls fail, run: source ./set_adc.sh