{ "__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": "Detailed diagnostic metrics for troubleshooting llm-d inference server (Tier 2 metrics)", "editable": true, "fiscalYearStartMonth": 0, "graphTooltip": 0, "id": null, "links": [], "panels": [ { "collapsed": false, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 }, "id": 200, "panels": [], "title": "Model Serving", "type": "row" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "KV cache utilization percentage by pod and model", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "min": 0, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "yellow", "value": 0.7 }, { "color": "red", "value": 0.9 } ] }, "unit": "percentunit" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 1 }, "id": 201, "options": { "legend": { "calcs": ["max", "mean", "lastNotNull"], "displayMode": "table", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "avg by(pod) (vllm:kv_cache_usage_perc{namespace=~\"$namespace\",model_name=~\"$model_name\"})", "instant": false, "legendFormat": "{{pod}}-{{model_name}}", "range": true, "refId": "A" } ], "title": "KV Cache Utilization", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Number of requests waiting in queue by pod and model", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] } }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 1 }, "id": 202, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "sum by(pod) (vllm:num_requests_waiting{namespace=~\"$namespace\",model_name=~\"$model_name\"})", "instant": false, "legendFormat": "{{pod}}-{{model_name}}", "range": true, "refId": "A" } ], "title": "Request Queue Lengths", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Total token throughput (prompt + generation tokens) per second by model and pod", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "tps" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 9 }, "id": 203, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "sum by(model_name, pod) (rate(vllm:prompt_tokens_total{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m]) + rate(vllm:generation_tokens_total{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m]))", "instant": false, "legendFormat": "{{model_name}}-{{pod}}", "range": true, "refId": "A" } ], "title": "Model Throughput", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Generation token rate per second by model and pod", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "tps" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 9 }, "id": 204, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "sum by(model_name, pod) (rate(vllm:generation_tokens_total{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m]))", "instant": false, "legendFormat": "{{model_name}}-{{pod}}", "range": true, "refId": "A" } ], "title": "Generation Token Rate", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Average number of running requests per pod (queue utilization)", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] } }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 17 }, "id": 205, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "avg by(pod) (vllm:num_requests_running{namespace=~\"$namespace\",model_name=~\"$model_name\"})", "instant": false, "legendFormat": "{{pod}}", "range": true, "refId": "A" } ], "title": "Queue Utilization", "type": "timeseries" }, { "collapsed": false, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 25 }, "id": 300, "panels": [], "title": "Routing", "type": "row" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Request distribution (QPS) per vLLM instance", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "reqps" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 26 }, "id": 301, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "sum by(pod) (rate(inference_objective_request_total{target_model_name!=\"\",namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m]))", "instant": false, "legendFormat": "{{pod}}", "range": true, "refId": "A" } ], "title": "Request Distribution", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Token distribution (tokens/sec) per vLLM instance", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "tps" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 26 }, "id": 302, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "sum by(pod) (rate(vllm:prompt_tokens_total{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m]) + rate(vllm:generation_tokens_total{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m]))", "instant": false, "legendFormat": "{{pod}}", "range": true, "refId": "A" } ], "title": "Token Distribution", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Percentage of time GPUs are idle (not processing tokens)", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "max": 1, "min": 0, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "percentunit" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 34 }, "id": 303, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "1 - avg by(pod) (rate(vllm:iteration_tokens_total_count{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m]) > 0)", "instant": false, "legendFormat": "{{pod}}", "range": true, "refId": "A" } ], "title": "Idle GPU Time", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "P99 latency for routing decision by scheduler plugin", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "s" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 34 }, "id": 304, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "histogram_quantile(0.99, sum by(le, plugin_type) (rate(inference_extension_plugin_duration_seconds_bucket{namespace=~\"$namespace\"}[5m])))", "instant": false, "legendFormat": "{{plugin_type}}", "range": true, "refId": "A" } ], "title": "Routing Decision Latency", "type": "timeseries" }, { "collapsed": false, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 42 }, "id": 400, "panels": [], "title": "Prefix Caching", "type": "row" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Overall prefix cache hit rate across all instances", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "max": 1, "min": 0, "thresholds": { "mode": "absolute", "steps": [ { "color": "red", "value": null }, { "color": "yellow", "value": 0.5 }, { "color": "green", "value": 0.8 } ] }, "unit": "percentunit" }, "overrides": [] }, "gridPos": { "h": 8, "w": 8, "x": 0, "y": 43 }, "id": 401, "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": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "sum(rate(vllm:prefix_cache_hits_total{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m])) / sum(rate(vllm:prefix_cache_queries_total{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m]))", "instant": false, "legendFormat": "Hit Rate", "range": true, "refId": "A" } ], "title": "Prefix Cache Hit Rate", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Prefix cache hit rate by individual vLLM instance", "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": [], "max": 1, "min": 0, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] }, "unit": "percentunit" }, "overrides": [] }, "gridPos": { "h": 8, "w": 16, "x": 8, "y": 43 }, "id": 402, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "sum by(pod) (rate(vllm:prefix_cache_hits_total{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m])) / sum by(pod) (rate(vllm:prefix_cache_queries_total{namespace=~\"$namespace\",model_name=~\"$model_name\"}[5m]))", "instant": false, "legendFormat": "{{pod}}", "range": true, "refId": "A" } ], "title": "Per-Instance Hit Rate", "type": "timeseries" }, { "collapsed": false, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 59 }, "id": 500, "panels": [], "title": "P/D Disaggregation", "type": "row" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Average number of running requests on prefill workers", "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": 8, "w": 12, "x": 0, "y": 60 }, "id": 501, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "avg by(pod) (vllm:num_requests_running{pod=~\".*prefill.*\",namespace=~\"$namespace\",model_name=~\"$model_name\"})", "instant": false, "legendFormat": "{{pod}}", "range": true, "refId": "A" } ], "title": "Prefill Worker Utilization", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "KV cache usage percentage on decode workers", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 10, "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": [], "min": 0, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 0.8 } ] }, "unit": "percentunit" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 60 }, "id": 502, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "avg by(pod) (vllm:kv_cache_usage_perc{pod=~\".*decode.*\",namespace=~\"$namespace\",model_name=~\"$model_name\"})", "instant": false, "legendFormat": "{{pod}}", "range": true, "refId": "A" } ], "title": "Decode Worker Utilization", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "description": "Number of requests waiting in prefill worker queues", "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": 8, "w": 12, "x": 0, "y": 68 }, "id": 503, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, "editorMode": "code", "expr": "sum by(pod) (vllm:num_requests_waiting{pod=~\".*prefill.*\",namespace=~\"$namespace\",model_name=~\"$model_name\"})", "instant": false, "legendFormat": "{{pod}}", "range": true, "refId": "A" } ], "title": "Prefill Queue Length", "type": "timeseries" } ], "refresh": "", "schemaVersion": 40, "tags": [ "llm-d", "monitoring", "vllm", "diagnostic", "drilldown" ], "templating": { "list": [ { "current": {}, "includeAll": false, "label": "datasource", "name": "DS_PROMETHEUS", "options": [], "query": "prometheus", "refresh": 1, "regex": "", "type": "datasource" }, { "current": {}, "datasource": { "type": "prometheus", "uid": "${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 Diagnostic Drill-Down", "uid": "llm-d-diagnostic-drilldown", "version": 1, "weekStart": "" }