This message was deleted.
# ask-for-help
s
This message was deleted.
🍱 1
👀 1
s
Custom runners are quite flexible and should be able to support all Python model runtimes, see https://docs.bentoml.org/en/latest/concepts/runner.html#custom-model-runner. Some examples can be found in https://github.com/bentoml/BentoML/tree/main/examples/custom_model_runner
m
Hi @Sean thanks for you feedback! But how to load specific folder containing converted model by CTranslate2?
Hi @Sean, I managed to use it with custom runner. However, how can I specify
batchable=True
since there is no
save_model
method with model signature?
s
Great work!
batchable=True
can be specified as a Runnable decorator.
Copy code
@bentoml.Runnable.method(batchable=False)
    def is_spam(self, input_data: NDArray[Any]) -> NDArray[Any]:
        return self.classifier.predict(input_data)
More details here, https://docs.bentoml.org/en/latest/concepts/runner.html#custom-model-runner