{ "__inputs": [ { "name": "DS_PROMETHEUS", "label": "prometheus", "description": "", "type": "datasource", "pluginId": "prometheus", "pluginName": "Prometheus" } ], "__elements": {}, "__requires": [ { "type": "grafana", "id": "grafana", "name": "Grafana", "version": "11.3.0" }, { "type": "panel", "id": "timeseries", "name": "Time series", "version": "" }, { "type": "datasource", "id": "prometheus", "name": "Prometheus", "version": "1.0.0" }, { "type": "panel", "id": "stat", "name": "Stat", "version": "" } ], "annotations": { "list": [ { "builtIn": 1, "datasource": { "type": "grafana", "uid": "-- Grafana --" }, "enable": true, "hide": true, "iconColor": "rgba(0, 211, 255, 1)", "name": "Annotations & Alerts", "target": { "limit": 100, "matchAny": false, "tags": [], "type": "dashboard" }, "type": "dashboard" } ] }, "description": "Key failure and saturation indicators for llm-d inference server (Tier 1 metrics)", "editable": true, "fiscalYearStartMonth": 0, "graphTooltip": 0, "id": null, "links": [], "panels": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Overall platform-wide error rate across all models", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "yellow", "value": 0.01 }, { "color": "red", "value": 0.05 } ] }, "unit": "percentunit" }, "overrides": [] }, "gridPos": { "h": 6, "w": 6, "x": 0, "y": 0 }, "id": 101, "options": { "colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": { "values": false, "calcs": [ "lastNotNull" ], "fields": "" }, "textMode": "auto", "wideLayout": true }, "pluginVersion": "11.3.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "sum(rate(inference_objective_request_error_total{namespace=~\"$namespace\"}[5m])) / sum(rate(inference_objective_request_total{namespace=~\"$namespace\"}[5m]))", "instant": false, "legendFormat": "Error Rate", "range": true, "refId": "A" } ], "title": "Overall Error Rate", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Error rate broken down by model name", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "percentunit" }, "overrides": [] }, "gridPos": { "h": 6, "w": 9, "x": 6, "y": 0 }, "id": 102, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "sum by(model_name) (rate(inference_objective_request_error_total{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m])) / sum by(model_name) (rate(inference_objective_request_total{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m]))", "instant": false, "legendFormat": "{{model_name}}", "range": true, "refId": "A" } ], "title": "Per-Model Error Rate", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Number of request preemptions per vLLM instance (indicates resource contention)", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] } }, "overrides": [] }, "gridPos": { "h": 6, "w": 9, "x": 15, "y": 0 }, "id": 103, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "sum by(pod) (rate(vllm:num_preemptions{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m]))", "instant": false, "legendFormat": "{{pod}}", "range": true, "refId": "A" } ], "title": "Request Preemptions", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "P50, P90, and P99 overall request latency across all models", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "s" }, "overrides": [] }, "gridPos": { "h": 8, "w": 8, "x": 0, "y": 6 }, "id": 104, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "histogram_quantile(0.50, sum by(le) (rate(inference_objective_request_duration_seconds_bucket{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m])))", "instant": false, "legendFormat": "P50", "range": true, "refId": "A" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "histogram_quantile(0.90, sum by(le) (rate(inference_objective_request_duration_seconds_bucket{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m])))", "hide": false, "instant": false, "legendFormat": "P90", "range": true, "refId": "B" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "histogram_quantile(0.99, sum by(le) (rate(inference_objective_request_duration_seconds_bucket{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m])))", "hide": false, "instant": false, "legendFormat": "P99", "range": true, "refId": "C" } ], "title": "Overall Latency P50/P90/P99", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "P99 Time to First Token latency by model (measures how long until response starts)", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "s" }, "overrides": [] }, "gridPos": { "h": 8, "w": 8, "x": 8, "y": 6 }, "id": 105, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "histogram_quantile(0.99, sum by(le, model_name) (rate(vllm:time_to_first_token_seconds_bucket{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m])))", "instant": false, "legendFormat": "{{model_name}}", "range": true, "refId": "A" } ], "title": "Model-Specific TTFT P99", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "P99 Inter-Token Latency by model (measures generation speed)", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "s" }, "overrides": [] }, "gridPos": { "h": 8, "w": 8, "x": 16, "y": 6 }, "id": 106, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "histogram_quantile(0.99, sum by(le, model_name) (rate(vllm:inter_token_latency_seconds_bucket{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m])))", "instant": false, "legendFormat": "{{model_name}}", "range": true, "refId": "A" } ], "title": "Model-Specific Inter-Token Latency P99", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Scheduler uptime and health indicator", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [ { "options": { "0": { "color": "red", "index": 1, "text": "Down" }, "1": { "color": "green", "index": 0, "text": "Up" } }, "type": "value" } ], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 0 }, { "color": "green", "value": 1 } ] } }, "overrides": [] }, "gridPos": { "h": 4, "w": 4, "x": 0, "y": 14 }, "id": 107, "options": { "colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": { "values": false, "calcs": [ "lastNotNull" ], "fields": "" }, "textMode": "auto", "wideLayout": true }, "pluginVersion": "11.3.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "avg_over_time(up{job=\"gaie-optimized-baseline-epp\",namespace=~\"$namespace\"}[5m])", "instant": false, "legendFormat": "Scheduler", "range": true, "refId": "A" } ], "title": "Scheduler Health", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Request rate (QPS) by model", "fieldConfig": { "defaults": { "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", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "reqps" }, "overrides": [] }, "gridPos": { "h": 8, "w": 10, "x": 14, "y": 14 }, "id": 109, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "sum by(model_name, target_model_name) (rate(inference_objective_request_total{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m]))", "instant": false, "legendFormat": "{{model_name}}", "range": true, "refId": "A" } ], "title": "Request Rate", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "P99 end-to-end latency through the EPP scheduler", "fieldConfig": { "defaults": { "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", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "s" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 22 }, "id": 110, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "histogram_quantile(0.99, sum by(le) (rate(inference_extension_scheduler_e2e_duration_seconds_bucket{namespace=~\"$namespace\"}[5m])))", "instant": false, "legendFormat": "P99", "range": true, "refId": "A" } ], "title": "EPP E2E Latency P99", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "P99 plugin processing latency by plugin type", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "s" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 22 }, "id": 111, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "histogram_quantile(0.99, sum by(le, plugin_type) (rate(inference_extension_plugin_duration_seconds_bucket{namespace=~\"$namespace\"}[5m])))", "instant": false, "legendFormat": "{{plugin_type}}", "range": true, "refId": "A" } ], "title": "Plugin Processing Latency", "type": "timeseries" } ], "refresh": "", "schemaVersion": 40, "tags": [ "llm-d", "monitoring", "vllm", "failure", "saturation" ], "templating": { "list": [ { "current": {}, "includeAll": false, "label": "datasource", "name": "DS_PROMETHEUS", "options": [], "query": "prometheus", "refresh": 1, "regex": "", "type": "datasource" }, { "current": {}, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "definition": "label_values(namespace)", "includeAll": true, "label": "namespace", "multi": true, "name": "namespace", "options": [], "query": { "qryType": 1, "query": "label_values(namespace)", "refId": "PrometheusVariableQueryEditor-VariableQuery" }, "refresh": 1, "regex": "", "type": "query" }, { "current": {}, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "definition": "label_values(vllm:generation_tokens_total,model_name)", "includeAll": true, "label": "model_name", "multi": true, "name": "model_name", "options": [], "query": { "qryType": 1, "query": "label_values(vllm:generation_tokens_total,model_name)", "refId": "PrometheusVariableQueryEditor-VariableQuery" }, "refresh": 2, "regex": "", "type": "query" } ] }, "time": { "from": "now-6h", "to": "now" }, "timepicker": {}, "timezone": "", "title": "llm-d Failure & Saturation Indicators", "uid": "llm-d-failure-saturation", "version": 1, "weekStart": "" }