why does model_run take much longer time than the actual execution of the operators? #24738
Unanswered
04633435
asked this question in
Performance Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
As you can see in the image above, the model_run spent a lot of time after the SequentialExecutor finished. What happened here under the hood, and is it possible to improve it to make the whole inference session run faster?
Beta Was this translation helpful? Give feedback.
All reactions