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
The unit would receive requests and aggregate them in a certain batch size.
The behaviour would be something like this:
Input transformation:
When receiving new request, store it in memory and wait (needs multithreading)
When enough requests have been received, returns a batch in one of them, nothing in the others
Output transformation:
Wait until all outputs have arrived
split the one containing the batch into all the others
return all
The text was updated successfully, but these errors were encountered:
* Initial data structures for experiment
* initial experiment commit
* Update for baseline experiments
* standalone experiments
* update control plane version and change header const name
* lint and updates to notebook and status server
* update notebook with new example and better utility methods
* kafka fixes while testing
* initial pipeline commit
* update tests
* change to remove explicit outputs
* updates
* refactor add pipeline
* lint
* add chainer server state setting£
* pipeline status updates
* order pipeline steps when creating proto
* lint
* review tests
* remove use of Is in tests
* fix errors in operator
* review comments
* review fixes
The unit would receive requests and aggregate them in a certain batch size.
The behaviour would be something like this:
Input transformation:
When receiving new request, store it in memory and wait (needs multithreading)
When enough requests have been received, returns a batch in one of them, nothing in the others
Output transformation:
Wait until all outputs have arrived
split the one containing the batch into all the others
return all
The text was updated successfully, but these errors were encountered: