{ "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": 1, "links": [], "panels": [ { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "description": "max-running-requests from server argument", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] } }, "overrides": [] }, "gridPos": { "h": 3, "w": 3, "x": 0, "y": 0 }, "id": 2, "options": { "colorMode": "value", "graphMode": "none", "justifyMode": "auto", "orientation": "auto", "percentChangeColorMode": "standard", "reduceOptions": { "calcs": [ "last" ], "fields": "", "values": false }, "showPercentChange": false, "textMode": "auto", "wideLayout": true }, "pluginVersion": "11.2.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "builder", "expr": "sglang:max_running_requests{name=\"$name\", instance=\"$instance\"}", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "__auto", "range": true, "refId": "A", "useBackend": false } ], "title": "Max Running Requests", "type": "stat" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "description": "Supported context length with loaded model", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] } }, "overrides": [] }, "gridPos": { "h": 3, "w": 3, "x": 3, "y": 0 }, "id": 1, "options": { "colorMode": "value", "graphMode": "none", "justifyMode": "auto", "orientation": "auto", "percentChangeColorMode": "standard", "reduceOptions": { "calcs": [ "last" ], "fields": "", "values": false }, "showPercentChange": false, "textMode": "auto", "wideLayout": true }, "pluginVersion": "11.2.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "builder", "expr": "sglang:context_len{instance=\"$instance\", name=\"$name\"}", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "__auto", "range": true, "refId": "A", "useBackend": false } ], "title": "Max Context Length", "type": "stat" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "description": "max_total_tokens", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] } }, "overrides": [] }, "gridPos": { "h": 3, "w": 3, "x": 6, "y": 0 }, "id": 4, "options": { "colorMode": "value", "graphMode": "none", "justifyMode": "auto", "orientation": "auto", "percentChangeColorMode": "standard", "reduceOptions": { "calcs": [ "last" ], "fields": "", "values": false }, "showPercentChange": false, "textMode": "auto", "wideLayout": true }, "pluginVersion": "11.2.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "builder", "expr": "sglang:max_total_num_tokens{instance=\"$instance\", name=\"$name\"}", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "__auto", "range": true, "refId": "A", "useBackend": false } ], "title": "Max Total Num Tokens", "type": "stat" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "description": "max_prefill_tokens from server args", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] } }, "overrides": [] }, "gridPos": { "h": 3, "w": 3, "x": 9, "y": 0 }, "id": 3, "options": { "colorMode": "value", "graphMode": "none", "justifyMode": "auto", "orientation": "auto", "percentChangeColorMode": "standard", "reduceOptions": { "calcs": [ "last" ], "fields": "", "values": false }, "showPercentChange": false, "textMode": "auto", "wideLayout": true }, "pluginVersion": "11.2.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "sglang:max_prefill_tokens{instance=\"$instance\", name=\"$name\"}", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "__auto", "range": true, "refId": "A", "useBackend": false } ], "title": "Max Prefill Tokens", "type": "stat" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] } }, "overrides": [] }, "gridPos": { "h": 3, "w": 6, "x": 12, "y": 0 }, "id": 6, "options": { "colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "percentChangeColorMode": "standard", "reduceOptions": { "calcs": [ "lastNotNull" ], "fields": "", "values": false }, "showPercentChange": false, "textMode": "auto", "wideLayout": true }, "pluginVersion": "11.2.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "sglang:cached_token{instance=\"$instance\", name=\"$name\"}", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "{{__name__}}", "range": true, "refId": "A", "useBackend": false } ], "title": "Cached Tokens", "type": "stat" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "description": "", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] } }, "overrides": [] }, "gridPos": { "h": 3, "w": 6, "x": 18, "y": 0 }, "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": "11.2.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "sglang:cache_hit_rate{instance=\"$instance\", name=\"$name\"}", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "{{__name__}}", "range": true, "refId": "A", "useBackend": false } ], "title": "Cache Hit Rate (%)", "type": "stat" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "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": 3 }, "id": 14, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "histogram_quantile(0.99, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{instance=\"$instance\", name=\"$name\"}[$__rate_interval])))", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "P99", "range": true, "refId": "A", "useBackend": false }, { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "histogram_quantile(0.9, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{instance=\"$instance\", name=\"$name\"}[$__rate_interval])))", "fullMetaSearch": false, "hide": false, "includeNullMetadata": true, "instant": false, "legendFormat": "P90", "range": true, "refId": "B", "useBackend": false }, { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "builder", "expr": "histogram_quantile(0.95, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{instance=\"$instance\", name=\"$model_name\"}[$__rate_interval])))", "fullMetaSearch": false, "hide": false, "includeNullMetadata": true, "instant": false, "legendFormat": "P95", "range": true, "refId": "C", "useBackend": false }, { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "builder", "expr": "histogram_quantile(0.5, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{instance=\"$instance\", name=\"$model_name\"}[$__rate_interval])))", "fullMetaSearch": false, "hide": false, "includeNullMetadata": true, "instant": false, "legendFormat": "P50", "range": true, "refId": "D", "useBackend": false }, { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "builder", "expr": "rate(sglang:e2e_request_latency_seconds_sum{instance=\"$instance\", name=\"$model_name\"}[$__rate_interval]) / rate(sglang:e2e_request_latency_seconds_count[$__rate_interval])", "fullMetaSearch": false, "hide": false, "includeNullMetadata": true, "instant": false, "legendFormat": "Average", "range": true, "refId": "E", "useBackend": false } ], "title": "E2E Request Latency (S)", "type": "timeseries" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "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": 3 }, "id": 18, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "editorMode": "code", "expr": "sglang:gen_throughput{instance=\"$instance\", name=\"$name\"}", "instant": false, "legendFormat": "__auto", "range": true, "refId": "A" } ], "title": "Generation Throughput (Token / S)", "type": "timeseries" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "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": 11 }, "id": 7, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "sglang:num_requests_running{instance=\"$instance\", name=\"$name\"}", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "{{__name__}}", "range": true, "refId": "A", "useBackend": false } ], "title": "Num Requests Running", "type": "timeseries" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "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": 11 }, "id": 8, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "sglang:num_requests_waiting{instance=\"$instance\", name=\"$name\"}", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "{{__name__}}", "range": true, "refId": "A", "useBackend": false } ], "title": "Number of Requests Waiting", "type": "timeseries" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "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": 19 }, "id": 16, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "histogram_quantile(0.99, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "P99", "range": true, "refId": "A", "useBackend": false }, { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "histogram_quantile(0.9, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))", "fullMetaSearch": false, "hide": false, "includeNullMetadata": true, "instant": false, "legendFormat": "P90", "range": true, "refId": "B", "useBackend": false }, { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "histogram_quantile(0.95, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))", "fullMetaSearch": false, "hide": false, "includeNullMetadata": true, "instant": false, "legendFormat": "P95", "range": true, "refId": "C", "useBackend": false }, { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "histogram_quantile(0.5, sum by(le) (rate(sglang:e2e_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))", "fullMetaSearch": false, "hide": false, "includeNullMetadata": true, "instant": false, "legendFormat": "P50", "range": true, "refId": "D", "useBackend": false }, { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "rate(sglang:e2e_request_latency_seconds_sum{name=\"$name\"}[$__rate_interval]) / rate(sglang:e2e_request_latency_seconds_count{name=\"$name\"}[$__rate_interval])", "fullMetaSearch": false, "hide": false, "includeNullMetadata": true, "instant": false, "legendFormat": "Average", "range": true, "refId": "E", "useBackend": false } ], "title": "Time Request Decoding (S)", "type": "timeseries" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "description": "Time requests waiting before added to batch", "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": 19 }, "id": 15, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "editorMode": "code", "expr": "histogram_quantile(0.99, sum by (le) (rate(sglang:waiting_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))", "instant": false, "legendFormat": "P99", "range": true, "refId": "A" }, { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "editorMode": "code", "expr": "histogram_quantile(0.95, sum by (le) (rate(sglang:waiting_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))", "hide": false, "instant": false, "legendFormat": "P95", "range": true, "refId": "B" }, { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "editorMode": "code", "expr": "histogram_quantile(0.9, sum by (le) (rate(sglang:waiting_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))", "hide": false, "instant": false, "legendFormat": "P90", "range": true, "refId": "C" }, { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "editorMode": "code", "expr": "histogram_quantile(0.5, sum by (le) (rate(sglang:waiting_request_latency_seconds_bucket{name=\"$name\"}[$__rate_interval])))", "hide": false, "instant": false, "legendFormat": "P50", "range": true, "refId": "D" }, { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "editorMode": "code", "expr": "rate(sglang:waiting_request_latency_seconds_sum{name=\"$name\"}[$__rate_interval])\r\n/\r\nrate(sglang:waiting_request_latency_seconds_count{name=\"$name\"}[$__rate_interval])", "hide": false, "instant": false, "legendFormat": "Average", "range": true, "refId": "E" } ], "title": "Time Request Waiting (S)", "type": "timeseries" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "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": 27 }, "id": 11, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "sum(rate(sglang:request_prompt_tokens_sum{instance=\"$instance\", name=\"$name\"}[$__rate_interval])) by (instance, name)", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "{{__name__}}", "range": true, "refId": "A", "useBackend": false }, { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "", "fullMetaSearch": false, "hide": false, "includeNullMetadata": true, "instant": false, "legendFormat": "__auto", "range": true, "refId": "B", "useBackend": false } ], "title": "Prompt Tokens", "type": "timeseries" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisBorderShow": false, "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "auto", "spanNulls": false, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] } }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 27 }, "id": 17, "options": { "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "sum(rate(sglang:request_generation_tokens_sum{instance=\"$instance\", name=\"$name\"}[$__rate_interval])) by (instance, name)", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "{{__name__}}", "range": true, "refId": "A", "useBackend": false } ], "title": "Generated Tokens", "type": "timeseries" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "fieldConfig": { "defaults": { "custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "scaleDistribution": { "type": "linear" } } }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 35 }, "id": 13, "options": { "calculate": false, "calculation": { "yBuckets": { "scale": { "log": 2, "type": "log" } } }, "cellGap": 1, "color": { "exponent": 0.5, "fill": "dark-orange", "mode": "scheme", "reverse": false, "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 } }, "pluginVersion": "11.2.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "sum by(le) (increase(sglang:request_prompt_tokens_bucket{name=\"$name\", instance=\"$instance\"}[$__rate_interval]))", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "{{__name__}}", "range": true, "refId": "A", "useBackend": false } ], "title": "Request Prompt Tokens", "type": "heatmap" }, { "datasource": { "default": true, "type": "prometheus", "uid": "ee2vha8w6f5kwf" }, "description": "", "fieldConfig": { "defaults": { "custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "scaleDistribution": { "type": "linear" } } }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 35 }, "id": 12, "options": { "calculate": false, "calculation": { "xBuckets": { "mode": "size", "value": "" }, "yBuckets": { "mode": "size", "scale": { "log": 2, "type": "log" }, "value": "" } }, "cellGap": 1, "color": { "exponent": 0.5, "fill": "dark-orange", "min": 0, "mode": "scheme", "reverse": false, "scale": "exponential", "scheme": "Spectral", "steps": 64 }, "exemplars": { "color": "rgba(255,0,255,0.7)" }, "filterValues": { "le": 1e-9 }, "legend": { "show": true }, "rowsFrame": { "layout": "auto", "value": "Request count" }, "tooltip": { "mode": "single", "showColorScale": false, "yHistogram": true }, "yAxis": { "axisLabel": "Generation Length", "axisPlacement": "left", "reverse": false, "unit": "none" } }, "pluginVersion": "11.2.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "disableTextWrap": false, "editorMode": "code", "expr": "sum by(le) (increase(sglang:request_generation_tokens_bucket{name=\"$name\", instance=\"$instance\"}[$__rate_interval]))", "fullMetaSearch": false, "includeNullMetadata": true, "instant": false, "legendFormat": "{{__name__}}", "range": true, "refId": "A", "useBackend": false } ], "title": "Request Generation Tokens", "type": "heatmap" } ], "refresh": "5s", "schemaVersion": 39, "tags": [], "templating": { "list": [ { "current": { "selected": false, "text": "127.0.0.1:30000", "value": "127.0.0.1:30000" }, "datasource": { "type": "prometheus", "uid": "ddyfngn31dg5cf" }, "definition": "label_values(instance)", "hide": 0, "includeAll": false, "label": "instance", "multi": false, "name": "instance", "options": [], "query": { "qryType": 1, "query": "label_values(instance)", "refId": "PrometheusVariableQueryEditor-VariableQuery" }, "refresh": 1, "regex": "", "skipUrlSync": false, "sort": 0, "type": "query" }, { "current": { "selected": true, "text": "google/gemma-2-9b-it", "value": "google/gemma-2-9b-it" }, "definition": "label_values(name)", "hide": 1, "includeAll": false, "label": "name", "multi": false, "name": "name", "options": [], "query": { "qryType": 1, "query": "label_values(name)", "refId": "PrometheusVariableQueryEditor-VariableQuery" }, "refresh": 1, "regex": "", "skipUrlSync": false, "sort": 0, "type": "query" } ] }, "time": { "from": "now-30m", "to": "now" }, "timepicker": {}, "timezone": "browser", "title": "SGLang Dashboard", "uid": "ddyp55uq7brpcc", "version": 3, "weekStart": "" }