serverside.yaml

- name: <string>  # API name (required)
  kind: RealtimeAPI
  predictor:
    type: python
    path: <string>  # path to a python file with a PythonPredictor class definition, relative to the Cortex root (required)
    server_side_batching:  # (optional)
      max_batch_size: <int>  # the maximum number of requests to aggregate before running inference
      batch_interval: <duration>  # the maximum amount of time to spend waiting for additional requests before running inference on the batch of requests