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 am new to using ollama and observing the following behavior.
I have an ollama server running on standard port.
when immich or opernwebui connect for some processing they start a runner and then it exits, so in the case of opern webui when no interaction is done the runner exits after a short period
for home assistant the runner is spawned on ollama and never exits, consuming considerable GPU memoru
my expectation is that once a conversation has had no interactions for a while the runner would end, freeing up GPU resources for other runners and saving about 1W of energy
i don't know what the intended behaviors is and if this is a design decision or a bug, i would expect it to function like other processes that use ollama and exit after a current conversation hasn't had activity for a while.
What version of Home Assistant Core has the issue?
core-2024.11.1
What was the last working version of Home Assistant Core?
Hey there @dmulcahey, mind taking a look at this issue as it has been labeled with an integration (flo) you are listed as a code owner for? Thanks!
Code owner commands
Code owners of flo can trigger bot actions by commenting:
@home-assistant close Closes the issue.
@home-assistant rename Awesome new title Renames the issue.
@home-assistant reopen Reopen the issue.
@home-assistant unassign flo Removes the current integration label and assignees on the issue, add the integration domain after the command.
@home-assistant add-label needs-more-information Add a label (needs-more-information, problem in dependency, problem in custom component) to the issue.
@home-assistant remove-label needs-more-information Remove a label (needs-more-information, problem in dependency, problem in custom component) on the issue.
The problem
I am new to using ollama and observing the following behavior.
my expectation is that once a conversation has had no interactions for a while the runner would end, freeing up GPU resources for other runners and saving about 1W of energy
i don't know what the intended behaviors is and if this is a design decision or a bug, i would expect it to function like other processes that use ollama and exit after a current conversation hasn't had activity for a while.
What version of Home Assistant Core has the issue?
core-2024.11.1
What was the last working version of Home Assistant Core?
No response
What type of installation are you running?
Home Assistant OS
Integration causing the issue
ollama
Link to integration documentation on our website
https://www.home-assistant.io/integrations/flo
Diagnostics information
No response
Example YAML snippet
No response
Anything in the logs that might be useful for us?
No response
Additional information
No response
The text was updated successfully, but these errors were encountered: