Initially it was complaining about it, but then when I did the connect_configuration it started working

The agent ip? Generally what’s the expected pattern to deploy and scale this for multiple models?

For now that's a quick thing, but for actual use I will need a proper model (pkl) and the .py

forking and using the latest code fixes the boto issue at least

don’t know what’s happening there

AgitatedDove14 - looks like the serving is doing the savemodel stuff?

https://github.com/allegroai/clearml-serving/blob/main/clearml_serving/serving_service.py#L554

Also btw, is this supposed to be screenshot from community verison? https://github.com/manojlds/clearml-serving/blob/main/docs/webapp_screenshots.gif

Model says PACKAGE, that means it’s fine right?

It did pick it from the task?

Yeah

That makes sense - one part I am confused on is - The Triton engine container hosts all the models right? Do we launch multiple gorups of these in different projects?

I used .update_weights(path) with path being the model dir containing the model.py annd the config.pbtxt. Should I use update_weights_package ?

Got the engine running.

curl <serving-engine-ip>:8000/v2/models/keras_mnist/versions/1What’s the serving-engine-ip supposed to be?

Yes, I have no experience with triton does it do lazy loading? Was wondering how it can handle 10s, 100s of models. If we load balance across a set of these engine containers with say 100 models and all of these models get traffic but distribution is not even, each of those engine container will load all those 100 models?

I am also not understanding how clearml-serving is doing the version for models in triton.

Think I will have to fork and play around with it 🙂

Without some sort of automation on top feels a bit fragile

Progress with boto3 added, but fails:

+1 to this question

I am essentially creating a EphemeralDataset abstraction and creating controlled lifecycle for it such that the data is removed after a day in experiments. Additionally and optionally, data created during a step in a pipeline can be cleared once the pipeline completes

So General would have created a General instead of Args?

What happens if I do blah/dataset_url ?

Yes, for datasets where we need GDPR compliance

Name is default None though?

Thanks

In params:

parameter_override={'General/dataset_urlWhat’s the General for?

barebones, can a step in a pipeline refer to a previous step by name and get it?

from here: https://github.com/allegroai/clearml/blob/5a9155b2039413280f13dfded1121470c4c4323d/examples/pipeline/pipeline_controller.py#L29

AgitatedDove14 is it possible to get the pipeline task running a step in a step? Is task.parent something that could help?

AgitatedDove14 - mean this - says name=None but text says default is General.