-
Notifications
You must be signed in to change notification settings - Fork 1
Open
Labels
Pri:P2Source:grafanaTeam:broken-vllmAlert label for Team:broken-vllmAlert label for Team:broken-vllmarea:alerting
Description
vLLM jobs have been broken on Trunk for at least three commits in a row. Please investigate.
Alert Details
- Occurred At: Oct 9, 9:00am PDT
- State: FIRING
- Team: broken-vllm
- Priority: P2
- Description: Detects when vLLM has been broken for too long
- Runbook: https://hud.pytorch.org
- Dashboard: https://pytorchci.grafana.net/d/e9a2a2e9-66d8-4ae3-ac6a-db76ab17321c?from=1760022050000&orgId=1&to=1760025710900
- View Alert: https://pytorchci.grafana.net/alerting/grafana/fezrlwnb9s2dca/view?orgId=1
- Silence Alert: https://pytorchci.grafana.net/alerting/silence/new?alertmanager=grafana&matcher=__alert_rule_uid__%3Dfezrlwnb9s2dca&matcher=rulename%3DvLLM+is+broken+-+3+commits+in+a+row+%28%3C%3D5+jobs+failing%29+%28copy%29&orgId=1
- Source: grafana
- Fingerprint:
4c99c139159eda2f1baa3997d3481f613c75be95bcce0435d0ffeedbc9f306eb
Metadata
Metadata
Assignees
Labels
Pri:P2Source:grafanaTeam:broken-vllmAlert label for Team:broken-vllmAlert label for Team:broken-vllmarea:alerting