Anyone dealt with defining datasets for blobs like model archives for TorchServe? Pretty straight forward use case, but was wondering if anyone else had tried anything 🙂

Do the different pickle options available not work?

Unfortunately not - TorchServe expects a model archive that contains various model artifacts and a customer_handler.py that handles loading the model, sticking it behind an API, and routing. https://github.com/pytorch/serve/blob/master/model-archiver/README.md I'll probably just create a simple Dataset that uploads / downloads the model-archive to the local FS and go from there. Just wanted to see what others might have come up with

I guess you could also subclass/work off

APIDataSet

to do the saving to the endpoint that way

That's a great idea! We deploy TorchServe instances per model given the types of models and pipelines we have but this might be useful in the future!

Out of interest (this is something tangental I’m working on) would you like it if your Kedro pipeline was a service that also lived as an endpoint?

It would certainly make deployment of models more seamless

super interesting thank you