[04:58:13] (03PS5) 10Kevin Bazira: llm: remove model-server [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/1062700 (https://phabricator.wikimedia.org/T369344) [05:08:45] (03CR) 10Kevin Bazira: [C:03+2] llm: remove model-server [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/1062700 (https://phabricator.wikimedia.org/T369344) (owner: 10Kevin Bazira) [05:18:18] (03Merged) 10jenkins-bot: llm: remove model-server [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/1062700 (https://phabricator.wikimedia.org/T369344) (owner: 10Kevin Bazira) [12:17:07] 06Machine-Learning-Team, 10MW-1.43-notes (1.43.0-wmf.19; 2024-08-20), 13Patch-For-Review, 10Structured-Data-Backlog (Current Work): [S] Update the logo detection service request to call the production endpoint - https://phabricator.wikimedia.org/T370762#10087554 (10kevinbazira) Hi @matthiasmullie, I have t... [12:29:35] * klausman late lunch [13:14:38] 06Machine-Learning-Team, 10MW-1.43-notes (1.43.0-wmf.19; 2024-08-20), 13Patch-For-Review, 10Structured-Data-Backlog (Current Work): [S] Update the logo detection service request to call the production endpoint - https://phabricator.wikimedia.org/T370762#10087702 (10matthiasmullie) Thanks for the pointer, @... [13:21:37] 06Machine-Learning-Team: Allow calling revertrisk language agnostic and revert risk multilingual APIs in a pre-save context - https://phabricator.wikimedia.org/T356102#10087741 (10achou) Hi @kostajh, sorry for the delay. Yes, I can deploy it to production next week. [13:23:52] Hey all [13:27:22] heyo Chris [13:59:24] https://gerrit.wikimedia.org/r/c/operations/deployment-charts/+/1065221 [14:00:56] ---^ open to better naming suggestions for this! [14:56:08] 06Machine-Learning-Team, 06DC-Ops, 10ops-codfw, 06SRE: ml-serve2002 memory errors on DIMM_B1 - https://phabricator.wikimedia.org/T365291#10088114 (10klausman) The problem with the alert is that it's ina a very spammy channel, and this particular alert happened about 1h after I had left for the day. I guess... [15:00:58] 06Machine-Learning-Team, 06DC-Ops, 10ops-codfw, 06SRE: ml-serve2002 memory errors on DIMM_B1 - https://phabricator.wikimedia.org/T365291#10088119 (10Jhancock.wm) I can get the offending DIMM card replaced today. Just need a little bit. @klausman [15:03:47] 06Machine-Learning-Team, 06DC-Ops, 10ops-codfw, 06SRE: ml-serve2002 memory errors on DIMM_B1 - https://phabricator.wikimedia.org/T365291#10088121 (10Dzahn) fwiw, I keep thinking that if the alert would simply be an email to the right list then it would be much more effective, not require realtime monitorin... [15:03:48] 06Machine-Learning-Team, 06DC-Ops, 10ops-codfw, 06SRE: ml-serve2002 memory errors on DIMM_B1 - https://phabricator.wikimedia.org/T365291#10088125 (10klausman) >>! In T365291#10088119, @Jhancock.wm wrote: > I can get the offending DIMM card replaced today. Just need a little bit. @klausman Thank you! The... [16:06:36] alright, heading out now. Have a nice weekend, everyone! [16:08:50] bye Tobias, have a nice weekend! [17:18:19] 06Machine-Learning-Team, 06DC-Ops, 10ops-codfw, 06SRE: ml-serve2002 memory errors on DIMM_B1 - https://phabricator.wikimedia.org/T365291#10088511 (10Jhancock.wm) @klausman it's been replaced and booted up. looks like the alert has cleared. lmk if you need any further assistance! [17:21:12] 06Machine-Learning-Team, 06DC-Ops, 10ops-codfw, 06SRE: ml-serve2002 memory errors on DIMM_B1 - https://phabricator.wikimedia.org/T365291#10088520 (10klausman) >>! In T365291#10088511, @Jhancock.wm wrote: > @klausman it's been replaced and booted up. looks like the alert has cleared. lmk if you need any fur... [18:22:37] 06Machine-Learning-Team, 10ORES, 06Discovery-Search, 06Growth-Team, 07OKR-Work: Investigate what would be required to include countries in ORES and accessible via a search keyword - https://phabricator.wikimedia.org/T301671#10088631 (10ldelench_wmf) [18:30:20] 10Lift-Wing, 06Machine-Learning-Team, 07OKR-Work: Request to host article-country model on Lift Wing - https://phabricator.wikimedia.org/T371897#10088677 (10ldelench_wmf) [20:32:20] 06Machine-Learning-Team, 10Automoderator, 10Moderator-Tools-Team (Kanban): [SPIKE]Perform a load test for Multilingual Revert Risk on LiftWing[4H] - https://phabricator.wikimedia.org/T372298#10089025 (10jsn.sherman) I did some more testing today, and out of a fresh ~15000 enwiki revision checks. results mult... [20:45:50] 06Machine-Learning-Team, 10Automoderator, 10Moderator-Tools-Team (Kanban): [SPIKE]Perform a load test for Multilingual Revert Risk on LiftWing[4H] - https://phabricator.wikimedia.org/T372298#10089042 (10diego) This looks great @jsn.sherman. Do you know if there is an overlap on the revisions that returns an... [21:49:48] 06Machine-Learning-Team, 10Automoderator, 10Moderator-Tools-Team (Kanban): [SPIKE]Perform a load test for Multilingual Revert Risk on LiftWing[4H] - https://phabricator.wikimedia.org/T372298#10089102 (10jsn.sherman) >>! In T372298#10089042, @diego wrote: > This looks great @jsn.sherman. Do you know if there...