{ "__inputs": [ { "name": "DS_PROMETHEUS", "label": "prometheus", "description": "", "type": "datasource", "pluginId": "prometheus", "pluginName": "Prometheus" } ], "__elements": {}, "__requires": [ { "type": "panel", "id": "gauge", "name": "Gauge", "version": "" }, { "type": "grafana", "id": "grafana", "name": "Grafana", "version": "10.4.3" }, { "type": "panel", "id": "heatmap", "name": "Heatmap", "version": "" }, { "type": "panel", "id": "piechart", "name": "Pie chart", "version": "" }, { "type": "datasource", "id": "prometheus", "name": "Prometheus", "version": "1.0.0" }, { "type": "panel", "id": "stat", "name": "Stat", "version": "" }, { "type": "panel", "id": "timeseries", "name": "Time series", "version": "" } ], "annotations": { "list": [ { "builtIn": 1, "datasource": { "type": "grafana", "uid": "-- Grafana --" }, "enable": true, "hide": true, "iconColor": "rgba(0, 211, 255, 1)", "name": "Annotations & Alerts", "type": "dashboard" } ] }, "editable": true, "fiscalYearStartMonth": 0, "graphTooltip": 0, "id": null, "links": [], "panels": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] }, "unit": "s" }, "overrides": [] }, "gridPos": { "h": 7, "w": 6, "x": 0, "y": 0 }, "id": 7, "options": { "colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false }, "showPercentChange": false, "textMode": "auto", "wideLayout": true }, "pluginVersion": "10.4.3", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "disableTextWrap": false, "editorMode": "builder", "expr": "histogram_quantile(0.5, sum by(le) (rate(time_to_first_token_seconds_bucket[$__rate_interval])))", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "__auto", "range": true, "refId": "A", "useBackend": false } ], "title": "Time to First Token (TTFT) p50", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] }, "unit": "s" }, "overrides": [] }, "gridPos": { "h": 7, "w": 6, "x": 6, "y": 0 }, "id": 6, "options": { "colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false }, "showPercentChange": false, "textMode": "auto", "wideLayout": true }, "pluginVersion": "10.4.3", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "disableTextWrap": false, "editorMode": "builder", "expr": "histogram_quantile(0.5, sum by(le) (rate(time_per_output_token_seconds_bucket[$__rate_interval])))", "format": "time_series", "fullMetaSearch": false, "includeNullMetadata": false, "instant": false, "legendFormat": "__auto", "range": true, "refId": "A", "useBackend": false } ], "title": "Inter-Token Latency (ITL) p50", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] } }, "overrides": [] }, "gridPos": { "h": 7, "w": 6, "x": 12, "y": 0 }, "id": 8, "options": { "colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false }, "showPercentChange": false, "textMode": "auto", "wideLayout": true }, "pluginVersion": "10.4.3", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "disableTextWrap": false, "editorMode": "builder", "expr": "rate(generation_tokens_total[$__rate_interval])", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "__auto", "range": true, "refId": "A", "useBackend": false } ], "title": "Throughput (tok/sec)", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false } }, "mappings": [] }, "overrides": [] }, "gridPos": { "h": 7, "w": 6, "x": 18, "y": 0 }, "id": 5, "options": { "displayLabels": [ "percent" ], "legend": { "displayMode": "list", "placement": "bottom", "showLegend": true }, "pieType": "donut", "reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "disableTextWrap": false, "editorMode": "code", "expr": "prompt_tokens_total", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "Context Tokens", "range": true, "refId": "A", "useBackend": false }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "disableTextWrap": false, "editorMode": "code", "expr": "generation_tokens_total", "fullMetaSearch": false, "hide": false, "includeNullMetadata": true, "instant": false, "legendFormat": "Generated Tokens", "range": true, "refId": "B", "useBackend": false } ], "title": "Context vs Generated Tokens", "type": "piechart" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] } }, "overrides": [ { "matcher": { "id": "byName", "options": "p50" }, "properties": [ { "id": "color", "value": { "fixedColor": "green", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "p90" }, "properties": [ { "id": "color", "value": { "fixedColor": "orange", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "p99" }, "properties": [ { "id": "color", "value": { "fixedColor": "red", "mode": "fixed" } } ] } ] }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 7 }, "id": 9, "options": { "legend": { "calcs": [ "min", "max" ], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "disableTextWrap": false, "editorMode": "code", "expr": "histogram_quantile(0.5, sum by(le) (rate(request_prompt_tokens_bucket[$__rate_interval])))", "format": "heatmap", "fullMetaSearch": false, "includeNullMetadata": false, "instant": false, "legendFormat": "p50", "range": true, "refId": "A", "useBackend": false }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "histogram_quantile(0.9, sum by(le) (rate(request_prompt_tokens_bucket[$__rate_interval])))", "hide": false, "instant": false, "legendFormat": "p90", "range": true, "refId": "B" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "histogram_quantile(0.99, sum by(le) (rate(request_prompt_tokens_bucket[$__rate_interval])))", "hide": false, "instant": false, "legendFormat": "p99", "range": true, "refId": "C" } ], "title": "Prompt Tokens", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "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", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] } }, "overrides": [ { "matcher": { "id": "byName", "options": "p50" }, "properties": [ { "id": "color", "value": { "fixedColor": "green", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "p90" }, "properties": [ { "id": "color", "value": { "fixedColor": "orange", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "p99" }, "properties": [ { "id": "color", "value": { "fixedColor": "red", "mode": "fixed" } } ] } ] }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 7 }, "id": 10, "options": { "legend": { "calcs": [ "min", "max" ], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "disableTextWrap": false, "editorMode": "code", "expr": "histogram_quantile(0.5, sum by(le) (rate(request_generation_tokens_bucket[$__rate_interval])))", "format": "heatmap", "fullMetaSearch": false, "includeNullMetadata": false, "instant": false, "legendFormat": "p50", "range": true, "refId": "A", "useBackend": false }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "histogram_quantile(0.9, sum by(le) (rate(request_generation_tokens_bucket[$__rate_interval])))", "hide": false, "instant": false, "legendFormat": "p90", "range": true, "refId": "B" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "histogram_quantile(0.99, sum by(le) (rate(request_generation_tokens_bucket[$__rate_interval])))", "hide": false, "instant": false, "legendFormat": "p99", "range": true, "refId": "C" } ], "title": "Generated Tokens", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "fieldConfig": { "defaults": { "custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "scaleDistribution": { "type": "linear" } } }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 15 }, "id": 1, "options": { "calculate": false, "cellGap": 1, "cellValues": { "decimals": 3, "unit": "none" }, "color": { "exponent": 0.5, "fill": "dark-orange", "mode": "scheme", "reverse": false, "scale": "exponential", "scheme": "Spectral", "steps": 64 }, "exemplars": { "color": "rgba(255,0,255,0.7)" }, "filterValues": { "le": 1e-9 }, "legend": { "show": true }, "rowsFrame": { "layout": "auto" }, "tooltip": { "mode": "single", "showColorScale": false, "yHistogram": false }, "yAxis": { "axisPlacement": "left", "reverse": false, "unit": "s" } }, "pluginVersion": "10.4.3", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "disableTextWrap": false, "editorMode": "builder", "exemplar": false, "expr": "rate(time_to_first_token_seconds_bucket[$__rate_interval])", "format": "heatmap", "fullMetaSearch": false, "includeNullMetadata": false, "instant": false, "legendFormat": "{{le}}", "range": true, "refId": "A", "useBackend": false } ], "title": "Time to First Token (TTFT)", "type": "heatmap" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "fieldConfig": { "defaults": { "custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "scaleDistribution": { "type": "linear" } } }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 15 }, "id": 4, "options": { "calculate": false, "cellGap": 1, "color": { "exponent": 0.5, "fill": "dark-orange", "mode": "scheme", "reverse": false, "scale": "exponential", "scheme": "Spectral", "steps": 64 }, "exemplars": { "color": "rgba(255,0,255,0.7)" }, "filterValues": { "le": 1e-9 }, "legend": { "show": true }, "rowsFrame": { "layout": "auto" }, "tooltip": { "mode": "single", "showColorScale": false, "yHistogram": false }, "yAxis": { "axisPlacement": "left", "reverse": false, "unit": "s" } }, "pluginVersion": "10.4.3", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "disableTextWrap": false, "editorMode": "builder", "expr": "rate(time_per_output_token_seconds_bucket[$__rate_interval])", "format": "heatmap", "fullMetaSearch": false, "includeNullMetadata": false, "instant": false, "legendFormat": "{{le}}", "range": true, "refId": "A", "useBackend": false } ], "title": "Inter Token Latency (ITL)", "type": "heatmap" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "percentunit" }, "overrides": [] }, "gridPos": { "h": 8, "w": 6, "x": 0, "y": 23 }, "id": 11, "options": { "colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false }, "showPercentChange": false, "textMode": "auto", "wideLayout": true }, "pluginVersion": "10.4.3", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "gpu_cache_usage_perc{}", "instant": false, "legendFormat": "__auto", "range": true, "refId": "A" } ], "title": "K/V Cache Utilization", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] } }, "overrides": [] }, "gridPos": { "h": 8, "w": 6, "x": 6, "y": 23 }, "id": 12, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "disableTextWrap": false, "editorMode": "builder", "expr": "rate(request_success_total[$__rate_interval])", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "__auto", "range": true, "refId": "A", "useBackend": false } ], "title": "Requests per second", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] } }, "overrides": [] }, "gridPos": { "h": 8, "w": 6, "x": 12, "y": 23 }, "id": 13, "options": { "minVizHeight": 75, "minVizWidth": 75, "orientation": "auto", "reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false }, "showThresholdLabels": false, "showThresholdMarkers": true, "sizing": "auto" }, "pluginVersion": "10.4.3", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "num_requests_waiting", "instant": false, "legendFormat": "__auto", "range": true, "refId": "A" } ], "title": "Requests Waiting", "type": "gauge" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] } }, "overrides": [] }, "gridPos": { "h": 8, "w": 6, "x": 18, "y": 23 }, "id": 14, "options": { "colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false }, "showPercentChange": false, "textMode": "auto", "wideLayout": true }, "pluginVersion": "10.4.3", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "num_requests_running", "instant": false, "legendFormat": "__auto", "range": true, "refId": "A" } ], "title": "Requests Running", "type": "stat" } ], "refresh": "", "schemaVersion": 39, "tags": [], "templating": { "list": [] }, "time": { "from": "now-30m", "to": "now" }, "timepicker": {}, "timezone": "browser", "title": "nim-dashboard", "uid": "bdml9450aom4gd", "version": 2, "weekStart": "" }