You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@beam.apache.org by "Anand Inguva (Jira)" <ji...@apache.org> on 2022/04/26 17:23:00 UTC

[jira] [Updated] (BEAM-14368) Investigate load state_dict vs loading whole model

     [ https://issues.apache.org/jira/browse/BEAM-14368?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Anand Inguva updated BEAM-14368:
--------------------------------
    Status: Triage Needed  (was: Open)

> Investigate load state_dict vs loading whole model
> --------------------------------------------------
>
>                 Key: BEAM-14368
>                 URL: https://issues.apache.org/jira/browse/BEAM-14368
>             Project: Beam
>          Issue Type: Sub-task
>          Components: sdk-py-core
>            Reporter: Anand Inguva
>            Assignee: Anand Inguva
>            Priority: P2
>              Labels: run-inference
>
> Loading pytorch model as whole has some issues with pickling. Investigate it with running some experiments. If the model size is too large, the current implementation of the RunInference for PyTorch would fail because of memory limits.



--
This message was sent by Atlassian Jira
(v8.20.7#820007)