[08:51:40] <elukey>	 hello folks
[08:51:50] <elukey>	 we have our POSIX group to deploy to our ML cluster
[08:52:04] <elukey>	 deploy-ml-service
[08:52:10] <elukey>	 with chrisalbon as approver
[08:52:22] <elukey>	 the initial members are the ML team ones of course :)
[09:48:04] <elukey>	 --
[09:48:18] <elukey>	 one thing that I was exploring atm is how ORES publishes metrics 
[09:48:40] <elukey>	 and it seems via statsd, that is captured by a local prometheus statsd exporter
[09:49:09] <elukey>	 we can add one to kubernetes, but I am wondering if our models do it
[09:49:23] <elukey>	 or if it is code buried in ORES 
[10:23:08] <elukey>	 https://blog.kubeflow.org/release/official/2021/09/27/kfserving-transition.html
[10:26:41] <wikibugs>	 10Lift-Wing, 10Machine-Learning-Team: Add prometheus metrics for KFServer-based model HTTP servers - https://phabricator.wikimedia.org/T292398 (10elukey)
[10:26:47] <elukey>	 opened --^
[16:25:15] <accraze>	 o/
[16:27:14] <elukey>	 o/
[17:10:19] * elukey afk!
[19:56:19] <wikibugs>	 10Machine-Learning-Team, 10artificial-intelligence, 10Wikilabels, 10articlequality-modeling: Build article quality model for Dutch Wikipedia - https://phabricator.wikimedia.org/T223782 (10Ciell) Send out the communication about the labeling campaign to the Dutch community just now.