You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm following the kepler-model-server startup guide. However, I noticed that on baremetal environment, setting NODE_COMPONENTS_ESTIMATOR=true doesn't have any effect. Noticed that it's disabled in the source code. Is it on purpose?
So if we want to use pre-trained model for power metrics on bare-metal model, does that mean we need to use PROCESS_COMPONENTS(/TOTAL)_ESTIMATOR config item(along with PROCESS_COMPONENTS_INIT_URL)? Does the pretrained model support that? I don't see any reference to the PROCESS_COMPONENTS_ESTIMATOR config in the documentation.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi all,
I'm following the kepler-model-server startup guide. However, I noticed that on baremetal environment, setting NODE_COMPONENTS_ESTIMATOR=true doesn't have any effect. Noticed that it's disabled in the source code. Is it on purpose?
So if we want to use pre-trained model for power metrics on bare-metal model, does that mean we need to use PROCESS_COMPONENTS(/TOTAL)_ESTIMATOR config item(along with PROCESS_COMPONENTS_INIT_URL)? Does the pretrained model support that? I don't see any reference to the PROCESS_COMPONENTS_ESTIMATOR config in the documentation.
p.s. I'm using manifest files to deploy kepler.
Beta Was this translation helpful? Give feedback.
All reactions