Monitoring
The tenant's inference metrics (RPS, error rate, p95 latency, data latency), training queue and GPU trends, and per-model performance and input distribution
Required permission: View
This screen shows whether the models in operation are running well. The top shows inference metrics for the whole tenant (Prometheus), the middle shows the training queue and GPU usage trends, and the bottom shows performance and input distribution once you choose a specific model. Every member can see it, and it is read-only.
| # | Area | Description |
|---|---|---|
| ① | Filters | All models (모델 전체) → one model, All edges (엣지 전체) → one device, range (1h · 24h · 7d · 30d). Filters are kept in the address, so you can share them as a link. |
| ② | Operational metrics | RPS (RPS) (requests per second) · Error rate (에러율) (%) · p95 latency (p95 지연) (ms) · Data latency (데이터 지연) (ms). The line below explains why a value is empty. |
| ③ | Training queue (학습 큐) | Trend of running and queued training runs. |
| ④ | GPU slots (GPU 슬롯) | Trend of wired slots and occupied slots. |
| ⑤ | Per-model card area | Once you choose a model, the model performance and input distribution cards appear. |
If the alerts feature is on and a KPI alert is firing, a KPI alerts firing (발생 중인 KPI 알림) line appears above ②, leading straight to that alert.
When you choose a model
| # | Card | Description |
|---|---|---|
| ① | Model performance (모델 성능) | Trends of accuracy, detection rate, mean confidence and low-confidence ratio. Filled in once ground-truth (GT) feedback from the field is aggregated. Always covers the whole period, regardless of the range filter. |
| ② | Input distribution / drift | Distribution per input feature, with PSI and KS values (7-day baseline). If there are many features, only 4 are shown. Drift verdicts and policies are handled on the Drift screen. |
Main tasks
When values are empty
| Notice shown | Meaning |
|---|---|
| The metrics source (Prometheus) is disabled, so values are empty (메트릭 소스(Prometheus)가 비활성화되어 값이 비어 있습니다) | The monitoring stack is not connected. Contact the system administrator. |
| No inference requests have reached this tenant yet (이 테넌트로 들어온 추론 요청이 아직 없습니다) | The connection is fine; values fill in once requests arrive. |
| No inference requests reached the selected model or edge in this period (선택한 모델·엣지로 들어온 추론 요청이 이 기간에 없습니다) | No requests match the filter. Try a longer range. |
| No recorded trend (기록된 추세 없음) | Trend metrics have not accumulated yet. |