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
When a user runs a job, if they have explicitly included a cache e.g.,
jobs.run(cache = my_cool_cache, ...)
and the job is run remotely, that cache should be sent to coop and used as the cache for running the job.
Similarly, if the user explicitly says cache = False we should not use a cache remotely.
If the user leaves the cache blank, we should use the coop universal cache (TBD).
This will require changes to:
Jobs
JobsRunnerAsyncI
Coop
JobsRemoteInferenceHandler
It will also require a modification to the coopr endpoint. Probably first step is to modify the coopr endpoint so it does not throw an exception when that cache is part of the payload.
Optional
In the job running log interface, we should probably also indicate the that job is being run with a cache in the logger / display.
The text was updated successfully, but these errors were encountered:
When a user runs a job, if they have explicitly included a cache e.g.,
and the job is run remotely, that cache should be sent to coop and used as the cache for running the job.
Similarly, if the user explicitly says
cache = False
we should not use a cache remotely.If the user leaves the cache blank, we should use the coop universal cache (TBD).
This will require changes to:
Jobs
JobsRunnerAsyncI
Coop
JobsRemoteInferenceHandler
It will also require a modification to the coopr endpoint. Probably first step is to modify the coopr endpoint so it does not throw an exception when that cache is part of the payload.
Optional
In the job running log interface, we should probably also indicate the that job is being run with a cache in the logger / display.
The text was updated successfully, but these errors were encountered: