pablobgar

Hi @adriangonz , Thanks for your response!! I understand your point, and I agree that the one you describe is going to be the most common use case. However, I...

I link this [related issue](https://github.com/SeldonIO/MLServer/issues/571) in which @erik-hasse raised a similar concern about having to open an issue and wait for new configs to be added whenever someone wants to...

Hi @adriangonz!! I understand that this has to be provided without support. Anyway it would be nice to have the possibility to do so assuming the consequences. In addition, it...

Hi @adriangonz Thanks for your quick response!! This is the content of i_request: ```` python {'id': None, 'parameters': {'content_type': 'pd', 'headers': None}, 'inputs': [{'name': 'col1', 'shape': [2], 'datatype': 'BYTES', 'parameters':...

This is the resulting request: ```` python model_name: "arte" parameters { key: "content_type" value { string_param: "pd" } } inputs { name: "col1" datatype: "BYTES" shape: 2 parameters { key:...

Hi @adriangonz I have the same result with `self.decode_request`. It seems that decoding is not performed in any case when the content type is bytes and PandasCodec is used. https://github.com/SeldonIO/MLServer/blob/1.1.0/mlserver/codecs/pandas.py#L17-L19

Hi @adriangonz Now it is working correctly if I add `Parameters(content_type=StringCodec.ContentType)`. Maybe I did something wrong when I tested it a few days ago, or I didn't test the combination...

Hi @adriangonz!! I was checking if there was something about traces when I came across this issue… and I would like to know what is the status of this task....

That's great news!! Thanks for your reply @adriangonz

Hey @adriangonz, I have added some k6 scripts to test the same scenario with grpc. As far as I can see, the differences are bigger than using rest. And even...