Commit ba09f6231966
Changed files (3)
systems
sakhalin
tools
ollama-exporter
systems/sakhalin/extra.nix
@@ -366,9 +366,11 @@ in
};
};
- # Create Grafana dashboard directory
+ # Create Grafana dashboard directory and deploy Ollama dashboards
systemd.tmpfiles.rules = [
"d /var/lib/grafana/dashboards 0755 grafana grafana -"
+ "C /var/lib/grafana/dashboards/ollama-metrics.json 0644 grafana grafana - ${../../tools/ollama-exporter/grafana-dashboard.json}"
+ "C /var/lib/grafana/dashboards/ollama-performance.json 0644 grafana grafana - ${../../tools/ollama-exporter/grafana-dashboard-custom.json}"
];
# Set Grafana admin password from secret file
tools/ollama-exporter/grafana-dashboard-custom.json
@@ -0,0 +1,882 @@
+{
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": {
+ "type": "grafana",
+ "uid": "-- Grafana --"
+ },
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "type": "dashboard"
+ }
+ ]
+ },
+ "editable": true,
+ "fiscalYearStartMonth": 0,
+ "graphTooltip": 0,
+ "id": 4,
+ "links": [],
+ "liveNow": false,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "vis": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "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
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "reqps"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 0
+ },
+ "id": 1,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr": "rate(ollama_requests_total[$__rate_interval])",
+ "instant": false,
+ "legendFormat": "{{model}}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Request Rate by Model",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 0
+ },
+ "id": 2,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "10.2.6",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr": "ollama_requests_total",
+ "instant": false,
+ "legendFormat": "{{model}}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Total Requests by Model",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "vis": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "s"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 8
+ },
+ "id": 3,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr": "rate(ollama_response_seconds_sum[$__rate_interval]) / rate(ollama_response_seconds_count[$__rate_interval])",
+ "instant": false,
+ "legendFormat": "Average - {{model}}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Average Response Time",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "vis": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "s"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 8
+ },
+ "id": 4,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr": "rate(ollama_load_duration_seconds_sum[$__rate_interval]) / rate(ollama_load_duration_seconds_count[$__rate_interval])",
+ "instant": false,
+ "legendFormat": "Average Load Time - {{model}}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Average Model Load Time",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "vis": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "never",
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "tps"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 16
+ },
+ "id": 5,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr": "rate(ollama_tokens_processed_total[$__rate_interval])",
+ "instant": false,
+ "legendFormat": "Input Tokens/s - {{model}}",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr": "rate(ollama_tokens_generated_total[$__rate_interval])",
+ "instant": false,
+ "legendFormat": "Output Tokens/s - {{model}}",
+ "range": true,
+ "refId": "B"
+ }
+ ],
+ "title": "Token Processing Rate",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "vis": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "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
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "tps"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 16
+ },
+ "id": 6,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr": "rate(ollama_tokens_per_second_sum[$__rate_interval]) / rate(ollama_tokens_per_second_count[$__rate_interval])",
+ "instant": false,
+ "legendFormat": "Average - {{model}}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Average Generation Speed (Tokens/Second)",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "vis": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "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
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "s"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 0,
+ "y": 24
+ },
+ "id": 7,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr": "rate(ollama_prompt_eval_duration_seconds_sum[$__rate_interval]) / rate(ollama_prompt_eval_duration_seconds_count[$__rate_interval])",
+ "instant": false,
+ "legendFormat": "Avg Prompt Eval - {{model}}",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr": "rate(ollama_eval_duration_seconds_sum[$__rate_interval]) / rate(ollama_eval_duration_seconds_count[$__rate_interval])",
+ "instant": false,
+ "legendFormat": "Avg Response Gen - {{model}}",
+ "range": true,
+ "refId": "B"
+ }
+ ],
+ "title": "Average Processing Time Breakdown",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "custom": {
+ "align": "auto",
+ "cellOptions": {
+ "type": "auto"
+ },
+ "inspect": false
+ },
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": null
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
+ },
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Avg Response Time"
+ },
+ "properties": [
+ {
+ "id": "unit",
+ "value": "s"
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Avg Tokens/Second"
+ },
+ "properties": [
+ {
+ "id": "unit",
+ "value": "tps"
+ }
+ ]
+ }
+ ]
+ },
+ "gridPos": {
+ "h": 8,
+ "w": 12,
+ "x": 12,
+ "y": 24
+ },
+ "id": 8,
+ "options": {
+ "cellHeight": "sm",
+ "footer": {
+ "countRows": false,
+ "fields": "",
+ "reducer": [
+ "sum"
+ ],
+ "show": false
+ },
+ "showHeader": true
+ },
+ "pluginVersion": "10.2.6",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr": "sum by (model) (ollama_requests_total)",
+ "format": "table",
+ "instant": true,
+ "legendFormat": "__auto",
+ "range": false,
+ "refId": "A"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr": "sum by (model) (ollama_response_seconds_sum) / sum by (model) (ollama_response_seconds_count)",
+ "format": "table",
+ "instant": true,
+ "legendFormat": "__auto",
+ "range": false,
+ "refId": "B"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "expr": "sum by (model) (ollama_tokens_per_second_sum) / sum by (model) (ollama_tokens_per_second_count)",
+ "format": "table",
+ "instant": true,
+ "legendFormat": "__auto",
+ "range": false,
+ "refId": "C"
+ }
+ ],
+ "title": "Model Performance Summary",
+ "transformations": [
+ {
+ "id": "merge",
+ "options": {}
+ },
+ {
+ "id": "organize",
+ "options": {
+ "excludeByName": {
+ "Time": true
+ },
+ "indexByName": {},
+ "renameByName": {
+ "Value #A": "Total Requests",
+ "Value #B": "Avg Response Time",
+ "Value #C": "Avg Tokens/Second",
+ "model": "Model"
+ }
+ }
+ }
+ ],
+ "type": "table"
+ }
+ ],
+ "refresh": "5s",
+ "schemaVersion": 39,
+ "tags": [
+ "ollama",
+ "ai",
+ "llm"
+ ],
+ "templating": {
+ "list": [
+ {
+ "current": {
+ "selected": false,
+ "text": "prometheus",
+ "value": "c09d1a89-4ff3-4c52-b8d5-dba793da5d90"
+ },
+ "hide": 0,
+ "includeAll": false,
+ "multi": false,
+ "name": "DS_PROMETHEUS",
+ "options": [],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "skipUrlSync": false,
+ "type": "datasource"
+ }
+ ]
+ },
+ "time": {
+ "from": "now-1h",
+ "to": "now"
+ },
+ "timepicker": {},
+ "timezone": "",
+ "title": "Ollama Performance Monitoring",
+ "uid": "ollama-dashboard",
+ "version": 1,
+ "weekStart": ""
+}
\ No newline at end of file
tools/ollama-exporter/grafana-dashboard.json
@@ -0,0 +1,517 @@
+{
+ "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": 15,
+ "links": [],
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 6,
+ "x": 0,
+ "y": 0
+ },
+ "id": 1,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "12.0.1",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "expr": "sum by (model) (ollama_requests_total)",
+ "format": "time_series",
+ "refId": "A"
+ }
+ ],
+ "title": "Total Requests Per Model",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "custom": {
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "scaleDistribution": {
+ "type": "linear"
+ }
+ }
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 15,
+ "w": 18,
+ "x": 6,
+ "y": 0
+ },
+ "id": 6,
+ "options": {
+ "calculate": false,
+ "cellGap": 1,
+ "color": {
+ "exponent": 0.5,
+ "fill": "dark-orange",
+ "mode": "scheme",
+ "reverse": true,
+ "scale": "exponential",
+ "scheme": "Oranges",
+ "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": "Tokens/s"
+ }
+ },
+ "pluginVersion": "12.0.1",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "editorMode": "code",
+ "expr": "ollama_tokens_per_second_bucket",
+ "format": "heatmap",
+ "hide": false,
+ "instant": false,
+ "legendFormat": "__auto",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Count of responses by Token/s",
+ "type": "heatmap"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "points",
+ "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"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 6,
+ "x": 0,
+ "y": 3
+ },
+ "id": 2,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "12.0.1",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "expr": "histogram_quantile(0.95, sum(rate(ollama_response_seconds_bucket[5m])) by (le, model))",
+ "format": "time_series",
+ "refId": "A"
+ }
+ ],
+ "title": "Response Time (Seconds)",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 6,
+ "x": 0,
+ "y": 6
+ },
+ "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": "12.0.1",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "expr": "sum by (model) (rate(ollama_tokens_generated_total[5m]))",
+ "format": "time_series",
+ "refId": "A"
+ }
+ ],
+ "title": "Tokens Generated Per Model",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "points",
+ "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"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 6,
+ "x": 0,
+ "y": 9
+ },
+ "id": 4,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "12.0.1",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "expr": "sum by (model) (rate(ollama_eval_total[5m]))",
+ "format": "time_series",
+ "refId": "A"
+ }
+ ],
+ "title": "Evaluation Steps",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "fenqsyb8rfke8c"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "points",
+ "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"
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 3,
+ "w": 6,
+ "x": 0,
+ "y": 12
+ },
+ "id": 5,
+ "options": {
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "12.0.1",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "expr": "histogram_quantile(0.95, sum(rate(ollama_load_time_seconds_bucket[5m])) by (le, model))",
+ "format": "time_series",
+ "refId": "A"
+ }
+ ],
+ "title": "Model Load Time (Seconds)",
+ "type": "timeseries"
+ }
+ ],
+ "preload": false,
+ "refresh": "5s",
+ "schemaVersion": 41,
+ "tags": [],
+ "templating": {
+ "list": []
+ },
+ "time": {
+ "from": "now-30m",
+ "to": "now"
+ },
+ "timepicker": {},
+ "timezone": "",
+ "title": "Ollama Metrics Dashboard",
+ "version": 2
+}
\ No newline at end of file