@Marvin Hrm, so when I launch a flow with a Dask cluster interactively in Jupyter, it runs fine. But when I try to do it in a Deployed flow from the GUI, the workers hang and never spin up. Any idea what could be causing that?

There could be a few things causing this issue. Here are some possibilities: 1. Cluster Configuration: The cluster configuration might be different between your interactive Jupyter session and the Prefect UI. You can specify the import path to the cluster class, the cluster class itself, or a function for creating a custom cluster when starting the flow run. You can also configure

cluster_kwargs

, which takes a dictionary of keyword arguments to pass to

cluster_class

when starting the flow run. Make sure these configurations are the same in both environments. More info here 2. Deployment Settings: Check your deployment settings in the Prefect UI. Make sure that the deployment has been created correctly and that you can inspect it using the CLI. More info here 3. Worker Management: There might be an issue with how your workers are being managed. For example, if you're trying to do a rolling upgrade of your workers while flows are actively running, this could cause issues. More info here If none of these suggestions help, could you provide more details about your setup? That might help me give a more specific answer.