# Example: Basic NIXLConnector configuration for prefill/decode disaggregation
# nixl_config.yaml

applications:
  - args:
      prefill_config:
        model_loading_config:
          model_id: meta-llama/Llama-3.1-8B-Instruct
        engine_kwargs:
          kv_transfer_config:
            kv_connector: NixlConnector
            kv_role: kv_producer
            engine_id: engine1
        deployment_config:
          autoscaling_config:
            min_replicas: 2
            max_replicas: 4
      
      decode_config:
        model_loading_config:
          model_id: meta-llama/Llama-3.1-8B-Instruct
        engine_kwargs:
          kv_transfer_config:
            kv_connector: NixlConnector
            kv_role: kv_consumer
            engine_id: engine2
        deployment_config:
          autoscaling_config:
            min_replicas: 6
            max_replicas: 10

    import_path: ray.serve.llm:build_pd_openai_app
    name: pd-disaggregation-nixl
    route_prefix: "/"