[04:29:06] 06Machine-Learning-Team, 10Wikimedia-Enterprise-Kanban-On-Call: Test liftwing wikidata revert risk API for scale and latency - https://phabricator.wikimedia.org/T409388#11560918 (10SGupta-WMF) **Run 3 results -** - Total Requests 146,231 - Successful Requests 136,287 - Failed Requests 9,944 - Success... [04:40:45] 06Machine-Learning-Team, 10Wikimedia-Enterprise-Kanban-On-Call: Test liftwing wikidata revert risk API for scale and latency - https://phabricator.wikimedia.org/T409388#11560922 (10SGupta-WMF) @kevinbazira @FNavas-foundation Key Takeaways from latest test - Throughput improved significantly, reaching ~136K... [04:41:25] 06Machine-Learning-Team, 10Wikimedia-Enterprise-Kanban-On-Call: Test liftwing wikidata revert risk API for scale and latency - https://phabricator.wikimedia.org/T409388#11560924 (10SGupta-WMF) [05:42:18] 06Machine-Learning-Team, 10Wikimedia-Enterprise-Kanban-On-Call: Test liftwing wikidata revert risk API for scale and latency - https://phabricator.wikimedia.org/T409388#11560986 (10kevinbazira) Thank you for sharing the load test results! >>! In T409388#11560918, @SGupta-WMF wrote: > Observed Errors > The in... [06:10:15] 06Machine-Learning-Team, 10Wikimedia-Enterprise-Kanban-On-Call: Test liftwing wikidata revert risk API for scale and latency - https://phabricator.wikimedia.org/T409388#11561038 (10SGupta-WMF) @kevinbazira Thank you for the suggestion! However, I wanted to clarify a few important points about WME's infrastruct... [13:54:39] 10Lift-Wing, 06Machine-Learning-Team: Add LiftWing streams data to event_sanitized (increase data retention) - https://phabricator.wikimedia.org/T405358#11562299 (10gkyziridis) >>! In T405358#11557401, @kostajh wrote: > @gkyziridis I'm testing this out today but only seeing `revertrisk-language-agnostic` for a... [14:32:52] 10Lift-Wing, 06Machine-Learning-Team: Add LiftWing streams data to event_sanitized (increase data retention) - https://phabricator.wikimedia.org/T405358#11562512 (10gkyziridis) We are currently do not store anywhere the predictions from the `rr-multilingual` model so we cannot export them in the same way that... [17:43:34] 06Machine-Learning-Team: Install AMD GPU + torch version of ML Labs machines - https://phabricator.wikimedia.org/T412357#11563375 (10Isaac) Two things: * I wanted to check in on this task and see when you all think this will be prioritized. No OKR-based urgency at the moment but I'm working on some evaluations f...