/doc/source/serve/doc_code/async_inference_autoscaling.yaml

# __basic_example_begin__
applications:
  - name: default
    import_path: my_module:app
    deployments:
      - name: MyConsumer
        max_ongoing_requests: 5
        autoscaling_config:
          min_replicas: 1
          max_replicas: 10
          target_ongoing_requests: 2
          policy:
            policy_function: "ray.serve.async_inference_autoscaling_policy:AsyncInferenceAutoscalingPolicy"
            policy_kwargs:
              broker_url: "redis://localhost:6379/0"
              queue_name: "my_queue"
# __basic_example_end__