[02:18:54] FIRING: [3x] SLOMetricAbsent: revertrisk-la-availability - https://slo.wikimedia.org/?search=revertrisk-la-availability - https://alerts.wikimedia.org/?q=alertname%3DSLOMetricAbsent [05:02:27] 10Lift-Wing, 06Machine-Learning-Team, 10Wikidata, 07OKR-Work: Optimize revertrisk-wikidata inference service to achieve ~500ms latency target - https://phabricator.wikimedia.org/T414060#11666478 (10kevinbazira) 05Open→03Resolved Closing this task as WME decided to proceed with the current deploymen... [05:08:41] 10Lift-Wing, 06Machine-Learning-Team, 10Wikidata, 06Wikimedia Enterprise, and 4 others: Q2 FY2025-26 Goal: Host Wikidata Revert Risk model on LiftWing - https://phabricator.wikimedia.org/T406179#11666483 (10kevinbazira) 05Open→03Resolved a:05gkyziridis→03kevinbazira **Weekly Update:** - WME dec... [06:19:13] FIRING: [3x] SLOMetricAbsent: revertrisk-la-availability - https://slo.wikimedia.org/?search=revertrisk-la-availability - https://alerts.wikimedia.org/?q=alertname%3DSLOMetricAbsent [07:53:02] (03CR) 10Nikerabbit: [C:03+2] Cache update: randomize sleep time after failure [research/recommendation-api] - 10https://gerrit.wikimedia.org/r/1240745 (owner: 10Sbisson) [07:54:45] (03CR) 10CI reject: [V:04-1] Cache update: randomize sleep time after failure [research/recommendation-api] - 10https://gerrit.wikimedia.org/r/1240745 (owner: 10Sbisson) [07:55:51] 06Machine-Learning-Team: Deploy gpt-oss-safeguard-20b on LiftWing - https://phabricator.wikimedia.org/T418350#11666643 (10kevinbazira) We noticed that although WMF members (e.g., ML, Research, etc.) have access to the ml-lab machine, the PSI team doesn't have access to ml-lab, and they have been running their te... [07:56:47] 06Machine-Learning-Team: Deploy gpt-oss-safeguard-20b on LiftWing - https://phabricator.wikimedia.org/T418350#11666644 (10kevinbazira) [08:57:33] 06Machine-Learning-Team, 05Goal: Q2 FY2025-26 Goal: Host a content policy evaluation model on LiftWing - https://phabricator.wikimedia.org/T418267#11666825 (10kostajh) [08:59:08] 06Machine-Learning-Team: Deploy CoPE-A on LiftWing - https://phabricator.wikimedia.org/T418832 (10kostajh) 03NEW [08:59:38] 06Machine-Learning-Team: Deploy CoPE-A on LiftWing - https://phabricator.wikimedia.org/T418832#11666839 (10kostajh) [09:30:03] 06Machine-Learning-Team, 06Product Safety and Integrity: Deploy CoPE-A on LiftWing - https://phabricator.wikimedia.org/T418832#11666958 (10kostajh) [10:19:33] FIRING: [3x] SLOMetricAbsent: revertrisk-la-availability - https://slo.wikimedia.org/?search=revertrisk-la-availability - https://alerts.wikimedia.org/?q=alertname%3DSLOMetricAbsent [12:04:27] 06Machine-Learning-Team, 06Product Safety and Integrity: Deploy CoPE-A on LiftWing - https://phabricator.wikimedia.org/T418832#11667636 (10BWojtowicz-WMF) I've managed to spin up the CoPE-A model on `ml-lab1002` machine on single MI210 GPU and tested it with sample request. Some important early findings: 1. F... [14:19:13] FIRING: [3x] SLOMetricAbsent: revertrisk-la-availability - https://slo.wikimedia.org/?search=revertrisk-la-availability - https://alerts.wikimedia.org/?q=alertname%3DSLOMetricAbsent [18:19:13] FIRING: [3x] SLOMetricAbsent: revertrisk-la-availability - https://slo.wikimedia.org/?search=revertrisk-la-availability - https://alerts.wikimedia.org/?q=alertname%3DSLOMetricAbsent [22:19:13] FIRING: [3x] SLOMetricAbsent: revertrisk-la-availability - https://slo.wikimedia.org/?search=revertrisk-la-availability - https://alerts.wikimedia.org/?q=alertname%3DSLOMetricAbsent