[08:27:03] 06Machine-Learning-Team: Add Wikidata RevertRisk predictions to mediawiki.page_revert_risk_prediction_change - https://phabricator.wikimedia.org/T420883 (10isarantopoulos) 03NEW [08:38:03] 06Machine-Learning-Team: Add Wikidata RevertRisk predictions to mediawiki.page_revert_risk_prediction_change - https://phabricator.wikimedia.org/T420883#11737001 (10isarantopoulos) [10:55:49] FIRING: KubernetesDeploymentUnavailableReplicas: ... [10:55:49] Deployment gpt-oss-safeguard-20b-predictor-00036-deployment in experimental at eqiad has persistently unavailable replicas - https://wikitech.wikimedia.org/wiki/Kubernetes/Troubleshooting#Troubleshooting_a_deployment - ... [10:55:53] https://grafana.wikimedia.org/d/a260da06-259a-4ee4-9540-5cab01a246c8/kubernetes-deployment-details?var-site=eqiad&var-cluster=k8s-mlserve&var-namespace=experimental&var-deployment=gpt-oss-safeguard-20b-predictor-00036-deployment - https://alerts.wikimedia.org/?q=alertname%3DKubernetesDeploymentUnavailableReplicas [11:00:49] RESOLVED: KubernetesDeploymentUnavailableReplicas: ... [11:00:49] Deployment gpt-oss-safeguard-20b-predictor-00036-deployment in experimental at eqiad has persistently unavailable replicas - https://wikitech.wikimedia.org/wiki/Kubernetes/Troubleshooting#Troubleshooting_a_deployment - ... [11:00:49] https://grafana.wikimedia.org/d/a260da06-259a-4ee4-9540-5cab01a246c8/kubernetes-deployment-details?var-site=eqiad&var-cluster=k8s-mlserve&var-namespace=experimental&var-deployment=gpt-oss-safeguard-20b-predictor-00036-deployment - https://alerts.wikimedia.org/?q=alertname%3DKubernetesDeploymentUnavailableReplicas [14:06:57] 06Machine-Learning-Team, 07OKR-Work: Load test current state of the Article Topic service - https://phabricator.wikimedia.org/T420931 (10BWojtowicz-WMF) 03NEW [14:21:38] 06Machine-Learning-Team, 07OKR-Work: Load test current state of the Article Topic service - https://phabricator.wikimedia.org/T420931#11738504 (10Isaac) > I'm using page_id and lang parameters, which offer the best performance. @BWojtowicz-WMF is `page_id` the only way to get cache support or would requesting... [14:36:08] 06Machine-Learning-Team, 07OKR-Work: Load test current state of the Article Topic service - https://phabricator.wikimedia.org/T420931#11738585 (10BWojtowicz-WMF) @Isaac The details of the cache and how exactly will it be implemented to Article Topics is still not fully decided. Current approaches we explored w... [14:45:36] 06Machine-Learning-Team, 07OKR-Work: Load test current state of the Article Topic service - https://phabricator.wikimedia.org/T420931#11738629 (10Isaac) > Current approaches we explored would work with page_id, whereas page_title requests would not go through cache. Understood -- at the point where you have to... [16:31:01] 06Machine-Learning-Team, 10Add-Link-Structured-Task, 06Growth-Team, 07Essential-Work, 07Wikimedia-production-error: MentionRegexException in link-recommendation service - https://phabricator.wikimedia.org/T420255#11739391 (10Michael) [16:33:19] 06Machine-Learning-Team, 10Add-Link-Structured-Task, 06Growth-Team, 07Essential-Work, 07Wikimedia-production-error: MentionRegexException in link-recommendation service - https://phabricator.wikimedia.org/T420255#11739414 (10OKarakaya-WMF) thank you @Michael , I'll check and let you know. [17:44:29] 06Machine-Learning-Team, 06Infrastructure-Foundations: Move the Docker Registry's /ml prefix to S3/apus - https://phabricator.wikimedia.org/T420978 (10elukey) 03NEW [17:44:58] 06Machine-Learning-Team, 06Infrastructure-Foundations: Move the Docker Registry's /ml prefix to S3/apus - https://phabricator.wikimedia.org/T420978#11739898 (10elukey) [22:37:49] FIRING: KubernetesDeploymentUnavailableReplicas: ... [22:37:49] Deployment gpt-oss-safeguard-20b-predictor-00002-deployment in experimental at eqiad has persistently unavailable replicas - https://wikitech.wikimedia.org/wiki/Kubernetes/Troubleshooting#Troubleshooting_a_deployment - ... [22:37:49] https://grafana.wikimedia.org/d/a260da06-259a-4ee4-9540-5cab01a246c8/kubernetes-deployment-details?var-site=eqiad&var-cluster=k8s-mlserve&var-namespace=experimental&var-deployment=gpt-oss-safeguard-20b-predictor-00002-deployment - https://alerts.wikimedia.org/?q=alertname%3DKubernetesDeploymentUnavailableReplicas