[
https://issues.apache.org/jira/browse/BEAM-13972?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17494207#comment-17494207
]
Andy Ye commented on BEAM-13972:
--------------------------------
Yes, the consensus from the
[design|[https://s.apache.org/inference-sklearn-pytorch]] is to use a single
RunInference wrapper. Inside the wrapper, depending which framework is being
used, then the appropriate implementation of RunInference will be called.
> Implement RunInference common interface
> ---------------------------------------
>
> Key: BEAM-13972
> URL: https://issues.apache.org/jira/browse/BEAM-13972
> Project: Beam
> Issue Type: Sub-task
> Components: sdk-py-core
> Reporter: Andy Ye
> Assignee: Andy Ye
> Priority: P2
> Labels: run-inference
>
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
