Issue when using bentoml 1.1.11 in the cloud vs using it in local

[xcadenas-veridas]

Hi!
I'm trying to set up BentoML 1.1.11, and I've managed to get it working locally. However, when I deploy the API on AWS, I get the following error:

  File "/usr/local/lib/python3.8/dist-packages/bentoml/_internal/runner/runner.py", line 52, in run
    return self.runner._runner_handle.run_method(self, *args, **kwargs)
  File "/usr/local/lib/python3.8/dist-packages/bentoml/_internal/runner/runner_handle/remote.py", line 346, in run_method
    anyio.from_thread.run(
  File "/usr/local/lib/python3.8/dist-packages/anyio/from_thread.py", line 48, in run
    return async_backend.run_async_from_thread(func, args, token=token)
  File "/usr/local/lib/python3.8/dist-packages/anyio/_backends/_asyncio.py", line 2143, in run_async_from_thread
    return f.result()
  File "/usr/lib/python3.8/concurrent/futures/_base.py", line 444, in result
    return self.__get_result()
  File "/usr/lib/python3.8/concurrent/futures/_base.py", line 389, in __get_result
    raise self._exception
  File "/usr/local/lib/python3.8/dist-packages/anyio/_backends/_asyncio.py", line 2130, in task_wrapper
    return await func(*args)
  File "/usr/local/lib/python3.8/dist-packages/bentoml/_internal/runner/runner_handle/remote.py", line 242, in async_run_method
    raise RemoteException(
bentoml.exceptions.RemoteException: An unexpected exception occurred in remote runner textbox_ocr_recognition: [404] Not Found

"POST http%3A//127.0.0.1%3A8000/model_response HTTP/1.1" 404

I can't replicate the issue locally. Is there some configuration I'm doing wrong? This is my configuration.yml:

api_server:
   workers: 1
   traffic:
     timeout: 100
   http:
     port: 5000

And this is how I define the runners:

class RunnableClass(bentoml.Runnable):
    SUPPORTED_RESOURCES = ("cpu",)
    SUPPORTS_CPU_MULTI_THREADING = True

    def __init__(self, model_artifact):
         self.artifact = model_artifact
         self.artifact.load(self.artifact.models_path)

    @bentoml.Runnable.method(batchable=False)
    def model_response(self, process_info):
        """
        """
        logger = get_logger(__name__)
        logger.info("%s detection request started",
                    process_info.get("process_name"))

        image_str = process_info.get("image")
        image = image_str2numpy(image_str)
        result = self.artifact.recognize(image)

        return result


model_runner = bentoml.Runner(
    RunnableClass,
    name="image_recognition",
    runnable_init_params={"model_name": "image_recognition",})


svc = bentoml.Service("service", runners=[model_runner])

@svc.api(input=JSON(), output=JSON())
def image_recognition(annotations: JSON, ctx: bentoml.Context):
     """
     """
     try:
         annotations["process_name"] = "image_recognition"
         with StopWatch(annotations["process_name"]):
             response = model_runner.\
                 model_response.run(process_info=annotations)
     except Exception as exception: 
         response = error_handler(exception)

     return response

Do you have any idea where the issue might be coming from?