Github user jegonzal commented on the pull request:
https://github.com/apache/spark/pull/3099#issuecomment-61922586
The model serving work would really benefit from being able to evaluate
models without requiring a Spark context especially since we are shooting for
10s millisecond latencies. Though more generally, we should think about how
one might want to use the artifact of the pipeline. I suspect their are uses
that may exist outside of Spark and the extent to which the models themselves
are "portable functions" could enable greater adoption.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
