apiVersion: dashboard.grafana.app/v2 kind: Dashboard metadata: name: addtgbw generation: 1 creationTimestamp: '2026-09-09T15:54:24Z' labels: {} annotations: {} spec: annotations: - kind: AnnotationQuery spec: query: kind: DataQuery group: grafana version: v0 spec: {} labels: grafana.app/export-label: grafana-1 enable: true hide: true iconColor: rgba(0, 211, 255, 1) name: Annotations & Alerts builtIn: true cursorSync: 'Off' description: '' editable: true elements: panel-1: kind: Panel spec: id: 1 title: TTFT description: '' links: [] data: kind: QueryGroup spec: queries: - kind: PanelQuery spec: query: kind: DataQuery group: prometheus version: v0 spec: editorMode: code expr: >- histogram_quantile(0.95, sum(rate(vllm:time_to_first_token_seconds_bucket[2m])) by (le)) legendFormat: __auto range: true labels: grafana.app/export-label: prometheus-1 grafana.app/export-datasource-name: Prometheus refId: A hidden: false transformations: [] queryOptions: {} vizConfig: kind: VizConfig group: timeseries version: 13.2.1 spec: options: legend: calcs: [] displayMode: list placement: bottom showLegend: true tooltip: hideZeros: false mode: single sort: none fieldConfig: defaults: thresholds: mode: absolute steps: - value: 0 color: green - value: 80 color: red color: mode: palette-classic custom: axisBorderShow: false axisCenteredZero: false axisColorMode: text axisLabel: '' axisPlacement: auto barAlignment: 0 barWidthFactor: 0.6 drawStyle: line fillOpacity: 0 gradientMode: none hideFrom: legend: false tooltip: false viz: false insertNulls: false lineInterpolation: linear lineWidth: 1 pointSize: 5 scaleDistribution: type: linear showPoints: auto showValues: false spanNulls: false stacking: group: A mode: none thresholdsStyle: mode: 'off' overrides: [] panel-2: kind: Panel spec: id: 2 title: TPOT description: '' links: [] data: kind: QueryGroup spec: queries: - kind: PanelQuery spec: query: kind: DataQuery group: prometheus version: v0 spec: editorMode: code expr: >- histogram_quantile(0.95, sum(rate(vllm:request_time_per_output_token_seconds_bucket[2m])) by (le)) legendFormat: __auto range: true labels: grafana.app/export-label: prometheus-1 grafana.app/export-datasource-name: Prometheus refId: A hidden: false transformations: [] queryOptions: {} vizConfig: kind: VizConfig group: timeseries version: 13.2.1 spec: options: legend: calcs: [] displayMode: list placement: bottom showLegend: true tooltip: hideZeros: false mode: single sort: none fieldConfig: defaults: thresholds: mode: absolute steps: - value: 0 color: green - value: 80 color: red color: mode: palette-classic custom: axisBorderShow: false axisCenteredZero: false axisColorMode: text axisLabel: '' axisPlacement: auto barAlignment: 0 barWidthFactor: 0.6 drawStyle: line fillOpacity: 0 gradientMode: none hideFrom: legend: false tooltip: false viz: false insertNulls: false lineInterpolation: linear lineWidth: 1 pointSize: 5 scaleDistribution: type: linear showPoints: auto showValues: false spanNulls: false stacking: group: A mode: none thresholdsStyle: mode: 'off' overrides: [] panel-3: kind: Panel spec: id: 3 title: Uso de memoria KV Cache description: '' links: [] data: kind: QueryGroup spec: queries: - kind: PanelQuery spec: query: kind: DataQuery group: prometheus version: v0 spec: editorMode: code expr: vllm:kv_cache_usage_perc * 100 legendFormat: __auto range: true labels: grafana.app/export-label: prometheus-1 grafana.app/export-datasource-name: Prometheus refId: A hidden: false transformations: [] queryOptions: {} vizConfig: kind: VizConfig group: gauge version: 13.2.1 spec: options: barShape: flat barWidthFactor: 0.5 effects: barGlow: false centerGlow: false gradient: true endpointMarker: point minVizHeight: 75 minVizWidth: 75 orientation: auto reduceOptions: calcs: - lastNotNull fields: '' values: false segmentCount: 1 segmentSpacing: 0.3 shape: gauge showThresholdLabels: false showThresholdMarkers: true sizing: auto sparkline: true textMode: auto fieldConfig: defaults: unit: percent min: 0 max: 100 thresholds: mode: absolute steps: - value: 0 color: green - value: 80 color: red color: mode: thresholds overrides: [] panel-4: kind: Panel spec: id: 4 title: Concurrencia en tiempo real description: '' links: [] data: kind: QueryGroup spec: queries: - kind: PanelQuery spec: query: kind: DataQuery group: prometheus version: v0 spec: editorMode: code expr: vllm:num_requests_running legendFormat: __auto range: true labels: grafana.app/export-label: prometheus-1 grafana.app/export-datasource-name: Prometheus refId: A hidden: false - kind: PanelQuery spec: query: kind: DataQuery group: prometheus version: v0 spec: editorMode: code expr: vllm:num_requests_waiting instant: false legendFormat: __auto range: true labels: grafana.app/export-label: prometheus-1 grafana.app/export-datasource-name: Prometheus refId: B hidden: false transformations: [] queryOptions: {} vizConfig: kind: VizConfig group: timeseries version: 13.2.1 spec: options: legend: calcs: [] displayMode: list placement: bottom showLegend: true tooltip: hideZeros: false mode: single sort: none fieldConfig: defaults: thresholds: mode: absolute steps: - value: 0 color: green - value: 80 color: red color: mode: palette-classic custom: axisBorderShow: false axisCenteredZero: false axisColorMode: text axisLabel: '' axisPlacement: auto barAlignment: 0 barWidthFactor: 0.6 drawStyle: line fillOpacity: 0 gradientMode: none hideFrom: legend: false tooltip: false viz: false insertNulls: false lineInterpolation: linear lineWidth: 1 pointSize: 5 scaleDistribution: type: linear showPoints: auto showValues: false spanNulls: false stacking: group: A mode: none thresholdsStyle: mode: 'off' overrides: [] panel-5: kind: Panel spec: id: 5 title: Latencia Total E2E description: '' links: [] data: kind: QueryGroup spec: queries: - kind: PanelQuery spec: query: kind: DataQuery group: prometheus version: v0 spec: editorMode: code expr: >- histogram_quantile(0.95, sum(rate(vllm:e2e_request_latency_seconds_bucket[2m])) by (le)) legendFormat: __auto range: true labels: grafana.app/export-label: prometheus-1 grafana.app/export-datasource-name: Prometheus refId: A hidden: false transformations: [] queryOptions: {} vizConfig: kind: VizConfig group: timeseries version: 13.2.1 spec: options: legend: calcs: [] displayMode: list placement: bottom showLegend: true tooltip: hideZeros: false mode: single sort: none fieldConfig: defaults: thresholds: mode: absolute steps: - value: 0 color: green - value: 80 color: red color: mode: palette-classic custom: axisBorderShow: false axisCenteredZero: false axisColorMode: text axisLabel: '' axisPlacement: auto barAlignment: 0 barWidthFactor: 0.6 drawStyle: line fillOpacity: 0 gradientMode: none hideFrom: legend: false tooltip: false viz: false insertNulls: false lineInterpolation: linear lineWidth: 1 pointSize: 5 scaleDistribution: type: linear showPoints: auto showValues: false spanNulls: false stacking: group: A mode: none thresholdsStyle: mode: 'off' overrides: [] layout: kind: AutoGridLayout spec: maxColumnCount: 3 columnWidthMode: standard rowHeightMode: standard items: - kind: AutoGridLayoutItem spec: element: kind: ElementReference name: panel-1 - kind: AutoGridLayoutItem spec: element: kind: ElementReference name: panel-2 - kind: AutoGridLayoutItem spec: element: kind: ElementReference name: panel-3 - kind: AutoGridLayoutItem spec: element: kind: ElementReference name: panel-4 - kind: AutoGridLayoutItem spec: element: kind: ElementReference name: panel-5 links: [] liveNow: false preload: false tags: [] timeSettings: timezone: browser from: now-6h to: now autoRefresh: '' autoRefreshIntervals: - 5s - 10s - 30s - 1m - 5m - 15m - 30m - 1h - 2h - 1d hideTimepicker: false fiscalYearStartMonth: 0 title: vLLM Panel variables: [] preferences: layout: kind: AutoGridLayout spec: maxColumnCount: 3 columnWidthMode: standard rowHeightMode: standard items: []