- name: single_deployment_1k_noop_replica
  team: serve
  cluster:
    app_config: app_config.yaml
    compute_template: compute_tpl_8_cpu.yaml

  run:
    timeout: 7200
    long_running: False
    script: python workloads/single_deployment_1k_noop_replica.py

  smoke_test:
    timeout: 600

- name: multi_deployment_1k_noop_replica
  team: serve
  cluster:
    app_config: app_config.yaml
    compute_template: compute_tpl_8_cpu.yaml

  run:
    timeout: 7200
    long_running: False
    script: python workloads/multi_deployment_1k_noop_replica.py

  smoke_test:
    timeout: 600

- name: autoscaling_single_deployment
  cluster:
    app_config: app_config.yaml
    compute_template: compute_tpl_8_cpu_autoscaling.yaml

  run:
    timeout: 7200
    long_running: False
    script: python workloads/autoscaling_single_deployment.py

  smoke_test:
    timeout: 600

- name: autoscaling_multi_deployment
  cluster:
    app_config: app_config.yaml
    compute_template: compute_tpl_8_cpu_autoscaling.yaml

  run:
    timeout: 7200
    long_running: False
    script: python workloads/autoscaling_multi_deployment.py

  smoke_test:
    timeout: 600

- name: serve_micro_benchmark
  team: serve
  cluster:
    app_config: app_config.yaml
    # 16 CPUS
    compute_template: compute_tpl_single_node.yaml

  run:
    timeout: 7200
    long_running: False
    script: python workloads/serve_micro_benchmark.py

  smoke_test:
    timeout: 600

- name: serve_micro_benchmark_k8s
  cluster:
    app_config: app_config.yaml
    # 16 CPUS
    compute_template: compute_tpl_single_node_k8s.yaml
    compute_on_k8s: True

  run:
    timeout: 7200
    long_running: False
    script: python workloads/serve_micro_benchmark.py

  smoke_test:
    timeout: 600

- name: serve_cluster_fault_tolerance
  team: serve
  cluster:
    app_config: app_config.yaml
    # 16 CPUS
    compute_template: compute_tpl_single_node.yaml

  run:
    timeout: 7200
    long_running: False
    script: python workloads/serve_cluster_fault_tolerance.py

  smoke_test:
    timeout: 600