{
  "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": [],
  "liveNow": false,
  "panels": [
    {
      "collapsed": false,
      "gridPos": {
        "h": 1,
        "w": 24,
        "x": 0,
        "y": 0
      },
      "id": 1,
      "panels": [],
      "title": "Overview",
      "type": "row"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "PBFA97CFB590B2093"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "thresholds"
          },
          "mappings": [
            {
              "options": {
                "0": {
                  "color": "red",
                  "index": 1,
                  "text": "Unhealthy"
                },
                "1": {
                  "color": "green",
                  "index": 0,
                  "text": "Healthy"
                }
              },
              "type": "value"
            }
          ],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "red",
                "value": null
              },
              {
                "color": "green",
                "value": 1
              }
            ]
          }
        },
        "overrides": []
      },
      "gridPos": {
        "h": 4,
        "w": 4,
        "x": 0,
        "y": 1
      },
      "id": 2,
      "options": {
        "colorMode": "background",
        "graphMode": "none",
        "justifyMode": "auto",
        "orientation": "auto",
        "reduceOptions": {
          "calcs": ["lastNotNull"],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "10.2.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "llm_backend_health",
          "refId": "A"
        }
      ],
      "title": "Backend Health",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "PBFA97CFB590B2093"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          },
          "unit": "reqps"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 4,
        "w": 4,
        "x": 4,
        "y": 1
      },
      "id": 3,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "reduceOptions": {
          "calcs": ["lastNotNull"],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "10.2.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "sum(rate(llm_requests_total[5m]))",
          "refId": "A"
        }
      ],
      "title": "Request Rate",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "PBFA97CFB590B2093"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              },
              {
                "color": "yellow",
                "value": 5
              },
              {
                "color": "red",
                "value": 10
              }
            ]
          },
          "unit": "s"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 4,
        "w": 4,
        "x": 8,
        "y": 1
      },
      "id": 4,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "reduceOptions": {
          "calcs": ["lastNotNull"],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "10.2.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "histogram_quantile(0.99, sum(rate(llm_request_duration_seconds_bucket[5m])) by (le))",
          "refId": "A"
        }
      ],
      "title": "P99 Latency",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "PBFA97CFB590B2093"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          },
          "unit": "none"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 4,
        "w": 4,
        "x": 12,
        "y": 1
      },
      "id": 5,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "reduceOptions": {
          "calcs": ["lastNotNull"],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "10.2.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "sum(rate(llm_completion_tokens_total[5m]))",
          "refId": "A"
        }
      ],
      "title": "Tokens/sec",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "PBFA97CFB590B2093"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              },
              {
                "color": "red",
                "value": 0.01
              }
            ]
          },
          "unit": "percentunit"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 4,
        "w": 4,
        "x": 16,
        "y": 1
      },
      "id": 6,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "reduceOptions": {
          "calcs": ["lastNotNull"],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "10.2.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "sum(rate(llm_errors_total[5m])) / sum(rate(llm_requests_total[5m])) or vector(0)",
          "refId": "A"
        }
      ],
      "title": "Error Rate",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "PBFA97CFB590B2093"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          },
          "unit": "none"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 4,
        "w": 4,
        "x": 20,
        "y": 1
      },
      "id": 7,
      "options": {
        "colorMode": "value",
        "graphMode": "none",
        "justifyMode": "auto",
        "orientation": "auto",
        "reduceOptions": {
          "calcs": ["lastNotNull"],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "pluginVersion": "10.2.0",
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "lora_adapters_loaded",
          "refId": "A"
        }
      ],
      "title": "LoRA Adapters",
      "type": "stat"
    },
    {
      "collapsed": false,
      "gridPos": {
        "h": 1,
        "w": 24,
        "x": 0,
        "y": 5
      },
      "id": 8,
      "panels": [],
      "title": "Request Metrics",
      "type": "row"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "PBFA97CFB590B2093"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisBorderShow": false,
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "drawStyle": "line",
            "fillOpacity": 10,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "insertNulls": false,
            "lineInterpolation": "smooth",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": {
              "type": "linear"
            },
            "showPoints": "never",
            "spanNulls": false,
            "stacking": {
              "group": "A",
              "mode": "none"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          },
          "unit": "reqps"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 0,
        "y": 6
      },
      "id": 9,
      "options": {
        "legend": {
          "calcs": ["mean", "max"],
          "displayMode": "table",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "desc"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "sum by (model) (rate(llm_requests_total[5m]))",
          "legendFormat": "{{model}}",
          "refId": "A"
        }
      ],
      "title": "Request Rate by Model",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "PBFA97CFB590B2093"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisBorderShow": false,
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "drawStyle": "line",
            "fillOpacity": 10,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "insertNulls": false,
            "lineInterpolation": "smooth",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": {
              "type": "linear"
            },
            "showPoints": "never",
            "spanNulls": false,
            "stacking": {
              "group": "A",
              "mode": "none"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          },
          "unit": "s"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 12,
        "y": 6
      },
      "id": 10,
      "options": {
        "legend": {
          "calcs": ["mean", "max"],
          "displayMode": "table",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "desc"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "histogram_quantile(0.50, sum(rate(llm_request_duration_seconds_bucket[5m])) by (le, model))",
          "legendFormat": "p50 {{model}}",
          "refId": "A"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "histogram_quantile(0.95, sum(rate(llm_request_duration_seconds_bucket[5m])) by (le, model))",
          "legendFormat": "p95 {{model}}",
          "refId": "B"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "histogram_quantile(0.99, sum(rate(llm_request_duration_seconds_bucket[5m])) by (le, model))",
          "legendFormat": "p99 {{model}}",
          "refId": "C"
        }
      ],
      "title": "Request Latency Percentiles",
      "type": "timeseries"
    },
    {
      "collapsed": false,
      "gridPos": {
        "h": 1,
        "w": 24,
        "x": 0,
        "y": 14
      },
      "id": 11,
      "panels": [],
      "title": "Token Metrics",
      "type": "row"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "PBFA97CFB590B2093"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisBorderShow": false,
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "drawStyle": "line",
            "fillOpacity": 10,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "insertNulls": false,
            "lineInterpolation": "smooth",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": {
              "type": "linear"
            },
            "showPoints": "never",
            "spanNulls": false,
            "stacking": {
              "group": "A",
              "mode": "none"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          },
          "unit": "none"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 0,
        "y": 15
      },
      "id": 12,
      "options": {
        "legend": {
          "calcs": ["mean", "max"],
          "displayMode": "table",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "desc"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "sum by (model) (rate(llm_completion_tokens_total[5m]))",
          "legendFormat": "Completion {{model}}",
          "refId": "A"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "sum by (model) (rate(llm_prompt_tokens_total[5m]))",
          "legendFormat": "Prompt {{model}}",
          "refId": "B"
        }
      ],
      "title": "Token Rate by Model",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "PBFA97CFB590B2093"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisBorderShow": false,
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "drawStyle": "line",
            "fillOpacity": 10,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "insertNulls": false,
            "lineInterpolation": "smooth",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": {
              "type": "linear"
            },
            "showPoints": "never",
            "spanNulls": false,
            "stacking": {
              "group": "A",
              "mode": "none"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          },
          "unit": "none"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 12,
        "y": 15
      },
      "id": 13,
      "options": {
        "legend": {
          "calcs": ["mean", "max"],
          "displayMode": "table",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "desc"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "histogram_quantile(0.50, sum(rate(llm_tokens_per_second_bucket[5m])) by (le, model))",
          "legendFormat": "p50 {{model}}",
          "refId": "A"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "histogram_quantile(0.95, sum(rate(llm_tokens_per_second_bucket[5m])) by (le, model))",
          "legendFormat": "p95 {{model}}",
          "refId": "B"
        }
      ],
      "title": "Tokens per Second",
      "type": "timeseries"
    },
    {
      "collapsed": false,
      "gridPos": {
        "h": 1,
        "w": 24,
        "x": 0,
        "y": 23
      },
      "id": 14,
      "panels": [],
      "title": "Errors & LoRA",
      "type": "row"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "PBFA97CFB590B2093"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisBorderShow": false,
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "drawStyle": "bars",
            "fillOpacity": 100,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "insertNulls": false,
            "lineInterpolation": "linear",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": {
              "type": "linear"
            },
            "showPoints": "never",
            "spanNulls": false,
            "stacking": {
              "group": "A",
              "mode": "normal"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          },
          "unit": "none"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 0,
        "y": 24
      },
      "id": 15,
      "options": {
        "legend": {
          "calcs": ["sum"],
          "displayMode": "table",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "desc"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "sum by (error_type) (increase(llm_errors_total[5m]))",
          "legendFormat": "{{error_type}}",
          "refId": "A"
        }
      ],
      "title": "Errors by Type",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "PBFA97CFB590B2093"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisBorderShow": false,
            "axisCenteredZero": false,
            "axisColorMode": "text",
            "axisLabel": "",
            "axisPlacement": "auto",
            "barAlignment": 0,
            "drawStyle": "line",
            "fillOpacity": 10,
            "gradientMode": "none",
            "hideFrom": {
              "legend": false,
              "tooltip": false,
              "viz": false
            },
            "insertNulls": false,
            "lineInterpolation": "smooth",
            "lineWidth": 1,
            "pointSize": 5,
            "scaleDistribution": {
              "type": "linear"
            },
            "showPoints": "never",
            "spanNulls": false,
            "stacking": {
              "group": "A",
              "mode": "none"
            },
            "thresholdsStyle": {
              "mode": "off"
            }
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          },
          "unit": "reqps"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 12,
        "y": 24
      },
      "id": 16,
      "options": {
        "legend": {
          "calcs": ["mean", "max"],
          "displayMode": "table",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "desc"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "PBFA97CFB590B2093"
          },
          "expr": "sum by (adapter_name) (rate(lora_adapter_requests_total[5m]))",
          "legendFormat": "{{adapter_name}}",
          "refId": "A"
        }
      ],
      "title": "LoRA Adapter Usage",
      "type": "timeseries"
    }
  ],
  "refresh": "10s",
  "schemaVersion": 38,
  "tags": ["local-llm", "inference"],
  "templating": {
    "list": []
  },
  "time": {
    "from": "now-1h",
    "to": "now"
  },
  "timepicker": {},
  "timezone": "browser",
  "title": "Local LLM Agent",
  "uid": "local-llm-agent",
  "version": 1,
  "weekStart": ""
}