{
  "annotations": {
    "list": [
      {
        "builtIn": 1,
        "datasource": {
          "type": "grafana",
          "uid": "-- Grafana --"
        },
        "enable": true,
        "hide": true,
        "iconColor": "rgba(0, 211, 255, 1)",
        "name": "Annotations & Alerts",
        "type": "dashboard"
      }
    ]
  },
  "description": "High-level overview of VLLM model deployment behavior and key performance indicators. Designed for Data Scientists and Product Managers to monitor request volume, token throughput, and latency",
  "editable": true,
  "fiscalYearStartMonth": 0,
  "graphTooltip": 0,
  "id": 47,
  "links": [],
  "panels": [
    {
      "collapsed": true,
      "gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
      "id": 20,
      "panels": [],
      "title": "Request Over Time",
      "type": "row"
    },
    {
      "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
      "fieldConfig": {
        "defaults": {
          "color": { "mode": "palette-classic" },
          "custom": {
            "axisBorderShow": false,
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "barWidthFactor": 0.6,
            "drawStyle": "line",
            "fillOpacity": 0,
            "gradientMode": "none",
            "hideFrom": { "legend": false, "tooltip": false, "viz": false },
            "insertNulls": false,
            "lineInterpolation": "linear",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": { "type": "linear" },
            "showPoints": "auto",
            "spanNulls": false,
            "stacking": { "group": "A", "mode": "none" },
            "thresholdsStyle": { "mode": "off" }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }]
          },
          "unit": "req/s"
        },
        "overrides": []
      },
      "gridPos": { "h": 6, "w": 10, "x": 0, "y": 1 },
      "id": 1,
      "options": {
        "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true },
        "tooltip": { "mode": "single", "sort": "none" }
      },
      "pluginVersion": "11.3.0",
      "targets": [
        {
          "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
          "editorMode": "code",
          "expr": "sum by (model_name) (\n  rate(vllm:request_success_total{model_name=~\"$Deployment_id\"}[$__rate_interval])\n)",
          "interval": "1",
          "legendFormat": "{{model_name}}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Successful Requests Over Time",
      "type": "timeseries"
    },
    {
      "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
      "fieldConfig": {
        "defaults": {
          "color": { "mode": "thresholds" },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }]
          },
          "unit": "req/s"
        },
        "overrides": []
      },
      "gridPos": { "h": 3, "w": 7, "x": 10, "y": 1 },
      "id": 2,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "percentChangeColorMode": "standard",
        "reduceOptions": { "calcs": ["mean"], "fields": "", "values": false },
        "showPercentChange": false,
        "textMode": "auto",
        "wideLayout": true
      },
      "pluginVersion": "11.3.0",
      "targets": [
        {
          "editorMode": "code",
          "expr": "sum(rate(vllm:request_success_total{model_name=~\"$Deployment_id\"}[$__rate_interval]))",
          "legendFormat": "__auto",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Requests Avg Rate",
      "type": "stat"
    },
    {
      "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
      "fieldConfig": {
        "defaults": {
          "color": { "mode": "thresholds" },
          "mappings": [
            { "options": { "Calcultaions": { "index": 0, "text": "Last (not null)" } }, "type": "value" }
          ],
          "thresholds": {
            "mode": "absolute",
            "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }]
          },
          "unit": "ms"
        },
        "overrides": []
      },
      "gridPos": { "h": 3, "w": 7, "x": 17, "y": 1 },
      "id": 3,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "percentChangeColorMode": "standard",
        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
        "showPercentChange": false,
        "textMode": "auto",
        "wideLayout": true
      },
      "pluginVersion": "11.3.0",
      "targets": [
        {
          "editorMode": "code",
          "expr": "histogram_quantile(0.50, sum by(le, model_name) (rate(vllm:e2e_request_latency_seconds_bucket{model_name=~\"$Deployment_id\"}[$__rate_interval])))",
          "legendFormat": "__auto",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "p50 Latency",
      "type": "stat"
    },
    {
      "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
      "fieldConfig": {
        "defaults": {
          "color": { "mode": "thresholds" },
          "mappings": [
            { "options": { "Calculation": { "index": 0, "text": "Last (not null)" } }, "type": "value" }
          ],
          "thresholds": {
            "mode": "absolute",
            "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }]
          },
          "unit": "ms"
        },
        "overrides": []
      },
      "gridPos": { "h": 3, "w": 7, "x": 10, "y": 4 },
      "id": 4,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "percentChangeColorMode": "standard",
        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
        "showPercentChange": false,
        "textMode": "auto",
        "wideLayout": true
      },
      "pluginVersion": "11.3.0",
      "targets": [
        {
          "editorMode": "code",
          "expr": "histogram_quantile(0.90, sum by(le, model_name) (rate(vllm:e2e_request_latency_seconds_bucket{model_name=~\"$Deployment_id\"}[$__rate_interval])))",
          "legendFormat": "__auto",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "p90 Latency",
      "type": "stat"
    },
    {
      "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
      "fieldConfig": {
        "defaults": {
          "color": { "mode": "thresholds" },
          "mappings": [
            { "options": { "Calculation": { "index": 0, "text": "Last (not null)" } }, "type": "value" }
          ],
          "thresholds": {
            "mode": "absolute",
            "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }]
          },
          "unit": "ms"
        },
        "overrides": []
      },
      "gridPos": { "h": 3, "w": 7, "x": 17, "y": 4 },
      "id": 5,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "percentChangeColorMode": "standard",
        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
        "showPercentChange": false,
        "textMode": "auto",
        "wideLayout": true
      },
      "pluginVersion": "11.3.0",
      "targets": [
        {
          "editorMode": "code",
          "expr": "histogram_quantile(0.99, sum by(le, model_name) (rate(vllm:e2e_request_latency_seconds_bucket{model_name=~\"$Deployment_id\"}[$__rate_interval])))",
          "legendFormat": "__auto",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "p99 Latency",
      "type": "stat"
    },
    {
      "collapsed": false,
      "gridPos": { "h": 1, "w": 24, "x": 0, "y": 7 },
      "id": 19,
      "panels": [],
      "title": "Size Distribution",
      "type": "row"
    },
    {
      "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
      "fieldConfig": {
        "defaults": {
          "color": { "mode": "palette-classic" },
          "custom": {
            "fillOpacity": 80,
            "gradientMode": "none",
            "hideFrom": { "legend": false, "tooltip": false, "viz": false },
            "lineWidth": 1,
            "stacking": { "group": "A", "mode": "none" }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }]
          },
          "unit": "cps"
        },
        "overrides": []
      },
      "gridPos": { "h": 6, "w": 10, "x": 0, "y": 8 },
      "id": 6,
      "options": {
        "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true },
        "tooltip": { "mode": "single", "sort": "none" }
      },
      "pluginVersion": "11.3.0",
      "targets": [
        {
          "editorMode": "code",
          "expr": "sum by (le, model_name) (rate(vllm:request_prompt_tokens_bucket{model_name=~\"$Deployment_id\"}[$__rate_interval]))",
          "legendFormat": "{{model_name}} le={{le}}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Input Token Size Distribution",
      "type": "histogram"
    },
    {
      "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
      "fieldConfig": {
        "defaults": {
          "color": { "mode": "thresholds" },
          "mappings": [
            { "options": { "calculation ": { "index": 0, "text": "Last (not null)" } }, "type": "value" }
          ],
          "thresholds": {
            "mode": "absolute",
            "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }]
          },
          "unit": "cps"
        },
        "overrides": []
      },
      "gridPos": { "h": 3, "w": 7, "x": 10, "y": 8 },
      "id": 9,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "percentChangeColorMode": "standard",
        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
        "showPercentChange": false,
        "textMode": "auto",
        "wideLayout": true
      },
      "pluginVersion": "11.3.0",
      "targets": [
        {
          "editorMode": "code",
          "expr": "histogram_quantile(0.90, sum by(le, model_name) (rate(vllm:request_prompt_tokens_bucket{model_name=~\"$Deployment_id\"}[$__rate_interval])))",
          "legendFormat": "__auto",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Input Token Size p90",
      "type": "stat"
    },
    {
      "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
      "fieldConfig": {
        "defaults": {
          "color": { "mode": "thresholds" },
          "mappings": [
            { "options": { "Calcultion": { "index": 0, "text": "Last (not null)" } }, "type": "value" }
          ],
          "thresholds": {
            "mode": "absolute",
            "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }]
          },
          "unit": "cps"
        },
        "overrides": []
      },
      "gridPos": { "h": 3, "w": 7, "x": 17, "y": 8 },
      "id": 8,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "percentChangeColorMode": "standard",
        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
        "showPercentChange": false,
        "textMode": "auto",
        "wideLayout": true
      },
      "pluginVersion": "11.3.0",
      "targets": [
        {
          "editorMode": "code",
          "expr": "histogram_quantile(0.50, sum by(le, model_name) (rate(vllm:request_prompt_tokens_bucket{model_name=~\"$Deployment_id\"}[$__rate_interval])))",
          "legendFormat": "__auto",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Input Token Size p50",
      "type": "stat"
    },
    {
      "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
      "fieldConfig": {
        "defaults": {
          "color": { "mode": "thresholds" },
          "mappings": [
            { "options": { "Calcultaion": { "index": 0, "text": "mean" } }, "type": "value" }
          ],
          "thresholds": {
            "mode": "absolute",
            "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }]
          },
          "unit": "cps"
        },
        "overrides": []
      },
      "gridPos": { "h": 3, "w": 7, "x": 10, "y": 11 },
      "id": 7,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "percentChangeColorMode": "standard",
        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
        "showPercentChange": false,
        "textMode": "auto",
        "wideLayout": true
      },
      "pluginVersion": "11.3.0",
      "targets": [
        {
          "editorMode": "code",
          "expr": "sum(rate(vllm:prompt_tokens_total{model_name=~\"$Deployment_id\"}[$__rate_interval]))\n/\nsum(rate(vllm:request_success_total{model_name=~\"$Deployment_id\"}[$__rate_interval]))",
          "legendFormat": "__auto",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Input Token Size Avg",
      "type": "stat"
    },
    {
      "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
      "fieldConfig": {
        "defaults": {
          "color": { "mode": "thresholds" },
          "mappings": [
            { "options": { "Calculation": { "index": 0, "text": "Last (not null)" } }, "type": "value" }
          ],
          "thresholds": {
            "mode": "absolute",
            "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }]
          },
          "unit": "cps"
        },
        "overrides": []
      },
      "gridPos": { "h": 3, "w": 7, "x": 17, "y": 11 },
      "id": 10,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "percentChangeColorMode": "standard",
        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
        "showPercentChange": false,
        "textMode": "auto",
        "wideLayout": true
      },
      "pluginVersion": "11.3.0",
      "targets": [
        {
          "editorMode": "code",
          "expr": "histogram_quantile(0.99, sum by(le, model_name) (rate(vllm:request_prompt_tokens_bucket{model_name=~\"$Deployment_id\"}[$__rate_interval])))",
          "legendFormat": "__auto",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Input Token Size p99",
      "type": "stat"
    },
    {
      "collapsed": true,
      "gridPos": { "h": 1, "w": 24, "x": 0, "y": 14 },
      "id": 18,
      "panels": [],
      "title": "Input Token Over Time",
      "type": "row"
    },
    {
      "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
      "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": "cps"
        },
        "overrides": []
      },
      "gridPos": { "h": 6, "w": 10, "x": 0, "y": 15 },
      "id": 11,
      "options": {
        "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true },
        "tooltip": { "mode": "single", "sort": "none" }
      },
      "pluginVersion": "11.3.0",
      "targets": [
        {
          "editorMode": "code",
          "expr": "sum by (model_name) (rate(vllm:prompt_tokens_total{model_name=~\"$Deployment_id\"}[$__rate_interval]))",
          "legendFormat": "{{model_name}}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Input Tokens Over Time",
      "type": "timeseries"
    },
    {
      "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
      "fieldConfig": {
        "defaults": {
          "color": { "mode": "thresholds" },
          "mappings": [
            { "options": { "Calculation": { "index": 0, "text": "mean" } }, "type": "value" }
          ],
          "thresholds": {
            "mode": "absolute",
            "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }]
          },
          "unit": "cps"
        },
        "overrides": []
      },
      "gridPos": { "h": 3, "w": 7, "x": 10, "y": 15 },
      "id": 12,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "percentChangeColorMode": "standard",
        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
        "showPercentChange": false,
        "textMode": "auto",
        "wideLayout": true
      },
      "pluginVersion": "11.3.0",
      "targets": [
        {
          "editorMode": "code",
          "expr": "sum(rate(vllm:prompt_tokens_total{model_name=~\"$Deployment_id\"}[$__rate_interval]))",
          "legendFormat": "__auto",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Input Tokens/Sec Avg",
      "type": "stat"
    },
    {
      "collapsed": false,
      "gridPos": { "h": 1, "w": 24, "x": 0, "y": 21 },
      "id": 17,
      "panels": [],
      "title": "Output Token Over Time",
      "type": "row"
    },
    {
      "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
      "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": "cps"
        },
        "overrides": []
      },
      "gridPos": { "h": 6, "w": 10, "x": 0, "y": 22 },
      "id": 13,
      "options": {
        "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true },
        "tooltip": { "mode": "single", "sort": "none" }
      },
      "pluginVersion": "11.3.0",
      "targets": [
        {
          "editorMode": "code",
          "expr": "sum by (model_name) (rate(vllm:generation_tokens_total{model_name=~\"$Deployment_id\"}[$__rate_interval]))",
          "legendFormat": "{{model_name}}",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Output Tokens Over Time",
      "type": "timeseries"
    },
    {
      "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
      "fieldConfig": {
        "defaults": {
          "color": { "mode": "thresholds" },
          "mappings": [
            { "options": { "Calculation": { "index": 0, "text": "mean" } }, "type": "value" }
          ],
          "thresholds": {
            "mode": "absolute",
            "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }]
          },
          "unit": "cps"
        },
        "overrides": []
      },
      "gridPos": { "h": 3, "w": 7, "x": 10, "y": 22 },
      "id": 14,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "percentChangeColorMode": "standard",
        "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
        "showPercentChange": false,
        "textMode": "auto",
        "wideLayout": true
      },
      "pluginVersion": "11.3.0",
      "targets": [
        {
          "editorMode": "code",
          "expr": "sum(rate(vllm:generation_tokens_total{model_name=~\"$Deployment_id\"}[$__rate_interval]))",
          "legendFormat": "__auto",
          "range": true,
          "refId": "A"
        }
      ],
      "title": "Output Tokens/Sec Avg",
      "type": "stat"
    }
  ],
  "preload": false,
  "schemaVersion": 40,
  "tags": [],
  "templating": {
    "list": [
      {
        "current": { "text": "Prometheus", "value": "4184fc20-68a7-483a-8d9b-7caa59c680dd" },
        "label": "datasource",
        "name": "DS_PROMETHEUS",
        "options": [],
        "query": "prometheus",
        "refresh": 1,
        "type": "datasource"
      },
      {
        "current": { "text": ["All"], "value": ["$__all"] },
        "definition": "label_values(vllm:request_success_total,model_name)",
        "includeAll": true,
        "label": "Deployment_ID",
        "multi": true,
        "name": "Deployment_id",
        "options": [],
        "query": {
          "qryType": 1,
          "query": "label_values(vllm:request_success_total,model_name)",
          "refId": "PrometheusVariableQueryEditor-VariableQuery"
        },
        "refresh": 1,
        "regex": "",
        "sort": 1,
        "type": "query"
      },
      {
        "current": { "text": "All hours", "value": "All hours" },
        "hide": 2,
        "label": "Rush Hours Only",
        "name": "rush_hours",
        "options": [
          { "selected": true, "text": "false", "value": "All hours" },
          { "selected": false, "text": "true", "value": "Rush hours" }
        ],
        "query": "false : All hours, true : Rush hours",
        "type": "custom"
      },
      {
        "current": { "text": "All", "value": "All" },
        "hide": 2,
        "label": "Rush Hours Type",
        "name": "rush_hours_type",
        "options": [
          { "selected": true, "text": "^All__.*$", "value": "All" },
          { "selected": false, "text": "^Static__.*$", "value": "Static" },
          { "selected": false, "text": "^Dynamic__.*$", "value": "Dynamic" }
        ],
        "query": "^All__.*$ : All, ^Static__.*$ : Static, ^Dynamic__.*$ : Dynamic",
        "type": "custom"
      },
      {
        "current": { "text": "", "value": "" },
        "hide": 2,
        "name": "query0",
        "options": [],
        "query": "",
        "refresh": 1,
        "regex": "",
        "type": "query"
      }
    ]
  },
  "time": { "from": "now-12h", "to": "now" },
  "timepicker": {},
  "timezone": "browser",
  "title": "Query Statistics_New4",
  "uid": "query-statistics4",
  "version": 2,
  "weekStart": ""
}