Flyte enables production-grade orchestration for machine learning workflows and data processing created to accelerate local workflows to production.

Flyte

so it should be possible to pickle and run tasks directly from notebook onto a flyte-server

I'm imagining map tasks from within notebook would be incredible

so i think we should just rewrite this resolverrr <https://github.com/flyteorg/flytekit/blob/master/flytekit/extras/cloud_pickle_resolver.py>

or use this resolver to use in fast-execute

and update pyflyte-fast-execute to use cloudpickle as an option

Also <@U019PBV483E> have you seen the new map-tasks

support for multiple-lists etc and partials?

this is in beta, some small bugs being fixed, but keep an eye

<https://github.com/flyteorg/flytekit/pull/1556>