| 1 | { |
| 2 | "annotations": { |
| 3 | "list": [ |
| 4 | { |
| 5 | "builtIn": 1, |
| 6 | "datasource": { |
| 7 | "type": "grafana", |
| 8 | "uid": "-- Grafana --" |
| 9 | }, |
| 10 | "enable": true, |
| 11 | "hide": true, |
| 12 | "iconColor": "rgba(0, 211, 255, 1)", |
| 13 | "name": "Annotations & Alerts", |
| 14 | "type": "dashboard" |
| 15 | } |
| 16 | ] |
| 17 | }, |
| 18 | "description": "High-level overview of VLLM model deployment behavior and key performance indicators. Designed for Data Scientists and Product Managers to monitor request volume, token throughput, and latency", |
| 19 | "editable": true, |
| 20 | "fiscalYearStartMonth": 0, |
| 21 | "graphTooltip": 0, |
| 22 | "id": 47, |
| 23 | "links": [], |
| 24 | "panels": [ |
| 25 | { |
| 26 | "collapsed": true, |
| 27 | "gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 }, |
| 28 | "id": 20, |
| 29 | "panels": [], |
| 30 | "title": "Request Over Time", |
| 31 | "type": "row" |
| 32 | }, |
| 33 | { |
| 34 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 35 | "fieldConfig": { |
| 36 | "defaults": { |
| 37 | "color": { "mode": "palette-classic" }, |
| 38 | "custom": { |
| 39 | "axisBorderShow": false, |
| 40 | "axisCenteredZero": false, |
| 41 | "axisColorMode": "text", |
| 42 | "axisLabel": "", |
| 43 | "axisPlacement": "auto", |
| 44 | "barAlignment": 0, |
| 45 | "barWidthFactor": 0.6, |
| 46 | "drawStyle": "line", |
| 47 | "fillOpacity": 0, |
| 48 | "gradientMode": "none", |
| 49 | "hideFrom": { "legend": false, "tooltip": false, "viz": false }, |
| 50 | "insertNulls": false, |
| 51 | "lineInterpolation": "linear", |
| 52 | "lineWidth": 1, |
| 53 | "pointSize": 5, |
| 54 | "scaleDistribution": { "type": "linear" }, |
| 55 | "showPoints": "auto", |
| 56 | "spanNulls": false, |
| 57 | "stacking": { "group": "A", "mode": "none" }, |
| 58 | "thresholdsStyle": { "mode": "off" } |
| 59 | }, |
| 60 | "mappings": [], |
| 61 | "thresholds": { |
| 62 | "mode": "absolute", |
| 63 | "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }] |
| 64 | }, |
| 65 | "unit": "req/s" |
| 66 | }, |
| 67 | "overrides": [] |
| 68 | }, |
| 69 | "gridPos": { "h": 6, "w": 10, "x": 0, "y": 1 }, |
| 70 | "id": 1, |
| 71 | "options": { |
| 72 | "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, |
| 73 | "tooltip": { "mode": "single", "sort": "none" } |
| 74 | }, |
| 75 | "pluginVersion": "11.3.0", |
| 76 | "targets": [ |
| 77 | { |
| 78 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 79 | "editorMode": "code", |
| 80 | "expr": "sum by (model_name) (\n rate(vllm:request_success_total{model_name=~\"$Deployment_id\"}[$__rate_interval])\n)", |
| 81 | "interval": "1", |
| 82 | "legendFormat": "{{model_name}}", |
| 83 | "range": true, |
| 84 | "refId": "A" |
| 85 | } |
| 86 | ], |
| 87 | "title": "Successful Requests Over Time", |
| 88 | "type": "timeseries" |
| 89 | }, |
| 90 | { |
| 91 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 92 | "fieldConfig": { |
| 93 | "defaults": { |
| 94 | "color": { "mode": "thresholds" }, |
| 95 | "mappings": [], |
| 96 | "thresholds": { |
| 97 | "mode": "absolute", |
| 98 | "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }] |
| 99 | }, |
| 100 | "unit": "req/s" |
| 101 | }, |
| 102 | "overrides": [] |
| 103 | }, |
| 104 | "gridPos": { "h": 3, "w": 7, "x": 10, "y": 1 }, |
| 105 | "id": 2, |
| 106 | "options": { |
| 107 | "colorMode": "value", |
| 108 | "graphMode": "area", |
| 109 | "justifyMode": "auto", |
| 110 | "orientation": "auto", |
| 111 | "percentChangeColorMode": "standard", |
| 112 | "reduceOptions": { "calcs": ["mean"], "fields": "", "values": false }, |
| 113 | "showPercentChange": false, |
| 114 | "textMode": "auto", |
| 115 | "wideLayout": true |
| 116 | }, |
| 117 | "pluginVersion": "11.3.0", |
| 118 | "targets": [ |
| 119 | { |
| 120 | "editorMode": "code", |
| 121 | "expr": "sum(rate(vllm:request_success_total{model_name=~\"$Deployment_id\"}[$__rate_interval]))", |
| 122 | "legendFormat": "__auto", |
| 123 | "range": true, |
| 124 | "refId": "A" |
| 125 | } |
| 126 | ], |
| 127 | "title": "Requests Avg Rate", |
| 128 | "type": "stat" |
| 129 | }, |
| 130 | { |
| 131 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 132 | "fieldConfig": { |
| 133 | "defaults": { |
| 134 | "color": { "mode": "thresholds" }, |
| 135 | "mappings": [ |
| 136 | { "options": { "Calcultaions": { "index": 0, "text": "Last (not null)" } }, "type": "value" } |
| 137 | ], |
| 138 | "thresholds": { |
| 139 | "mode": "absolute", |
| 140 | "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }] |
| 141 | }, |
| 142 | "unit": "ms" |
| 143 | }, |
| 144 | "overrides": [] |
| 145 | }, |
| 146 | "gridPos": { "h": 3, "w": 7, "x": 17, "y": 1 }, |
| 147 | "id": 3, |
| 148 | "options": { |
| 149 | "colorMode": "value", |
| 150 | "graphMode": "area", |
| 151 | "justifyMode": "auto", |
| 152 | "orientation": "auto", |
| 153 | "percentChangeColorMode": "standard", |
| 154 | "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, |
| 155 | "showPercentChange": false, |
| 156 | "textMode": "auto", |
| 157 | "wideLayout": true |
| 158 | }, |
| 159 | "pluginVersion": "11.3.0", |
| 160 | "targets": [ |
| 161 | { |
| 162 | "editorMode": "code", |
| 163 | "expr": "histogram_quantile(0.50, sum by(le, model_name) (rate(vllm:e2e_request_latency_seconds_bucket{model_name=~\"$Deployment_id\"}[$__rate_interval])))", |
| 164 | "legendFormat": "__auto", |
| 165 | "range": true, |
| 166 | "refId": "A" |
| 167 | } |
| 168 | ], |
| 169 | "title": "p50 Latency", |
| 170 | "type": "stat" |
| 171 | }, |
| 172 | { |
| 173 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 174 | "fieldConfig": { |
| 175 | "defaults": { |
| 176 | "color": { "mode": "thresholds" }, |
| 177 | "mappings": [ |
| 178 | { "options": { "Calculation": { "index": 0, "text": "Last (not null)" } }, "type": "value" } |
| 179 | ], |
| 180 | "thresholds": { |
| 181 | "mode": "absolute", |
| 182 | "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }] |
| 183 | }, |
| 184 | "unit": "ms" |
| 185 | }, |
| 186 | "overrides": [] |
| 187 | }, |
| 188 | "gridPos": { "h": 3, "w": 7, "x": 10, "y": 4 }, |
| 189 | "id": 4, |
| 190 | "options": { |
| 191 | "colorMode": "value", |
| 192 | "graphMode": "area", |
| 193 | "justifyMode": "auto", |
| 194 | "orientation": "auto", |
| 195 | "percentChangeColorMode": "standard", |
| 196 | "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, |
| 197 | "showPercentChange": false, |
| 198 | "textMode": "auto", |
| 199 | "wideLayout": true |
| 200 | }, |
| 201 | "pluginVersion": "11.3.0", |
| 202 | "targets": [ |
| 203 | { |
| 204 | "editorMode": "code", |
| 205 | "expr": "histogram_quantile(0.90, sum by(le, model_name) (rate(vllm:e2e_request_latency_seconds_bucket{model_name=~\"$Deployment_id\"}[$__rate_interval])))", |
| 206 | "legendFormat": "__auto", |
| 207 | "range": true, |
| 208 | "refId": "A" |
| 209 | } |
| 210 | ], |
| 211 | "title": "p90 Latency", |
| 212 | "type": "stat" |
| 213 | }, |
| 214 | { |
| 215 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 216 | "fieldConfig": { |
| 217 | "defaults": { |
| 218 | "color": { "mode": "thresholds" }, |
| 219 | "mappings": [ |
| 220 | { "options": { "Calculation": { "index": 0, "text": "Last (not null)" } }, "type": "value" } |
| 221 | ], |
| 222 | "thresholds": { |
| 223 | "mode": "absolute", |
| 224 | "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }] |
| 225 | }, |
| 226 | "unit": "ms" |
| 227 | }, |
| 228 | "overrides": [] |
| 229 | }, |
| 230 | "gridPos": { "h": 3, "w": 7, "x": 17, "y": 4 }, |
| 231 | "id": 5, |
| 232 | "options": { |
| 233 | "colorMode": "value", |
| 234 | "graphMode": "area", |
| 235 | "justifyMode": "auto", |
| 236 | "orientation": "auto", |
| 237 | "percentChangeColorMode": "standard", |
| 238 | "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, |
| 239 | "showPercentChange": false, |
| 240 | "textMode": "auto", |
| 241 | "wideLayout": true |
| 242 | }, |
| 243 | "pluginVersion": "11.3.0", |
| 244 | "targets": [ |
| 245 | { |
| 246 | "editorMode": "code", |
| 247 | "expr": "histogram_quantile(0.99, sum by(le, model_name) (rate(vllm:e2e_request_latency_seconds_bucket{model_name=~\"$Deployment_id\"}[$__rate_interval])))", |
| 248 | "legendFormat": "__auto", |
| 249 | "range": true, |
| 250 | "refId": "A" |
| 251 | } |
| 252 | ], |
| 253 | "title": "p99 Latency", |
| 254 | "type": "stat" |
| 255 | }, |
| 256 | { |
| 257 | "collapsed": false, |
| 258 | "gridPos": { "h": 1, "w": 24, "x": 0, "y": 7 }, |
| 259 | "id": 19, |
| 260 | "panels": [], |
| 261 | "title": "Size Distribution", |
| 262 | "type": "row" |
| 263 | }, |
| 264 | { |
| 265 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 266 | "fieldConfig": { |
| 267 | "defaults": { |
| 268 | "color": { "mode": "palette-classic" }, |
| 269 | "custom": { |
| 270 | "fillOpacity": 80, |
| 271 | "gradientMode": "none", |
| 272 | "hideFrom": { "legend": false, "tooltip": false, "viz": false }, |
| 273 | "lineWidth": 1, |
| 274 | "stacking": { "group": "A", "mode": "none" } |
| 275 | }, |
| 276 | "mappings": [], |
| 277 | "thresholds": { |
| 278 | "mode": "absolute", |
| 279 | "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }] |
| 280 | }, |
| 281 | "unit": "cps" |
| 282 | }, |
| 283 | "overrides": [] |
| 284 | }, |
| 285 | "gridPos": { "h": 6, "w": 10, "x": 0, "y": 8 }, |
| 286 | "id": 6, |
| 287 | "options": { |
| 288 | "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, |
| 289 | "tooltip": { "mode": "single", "sort": "none" } |
| 290 | }, |
| 291 | "pluginVersion": "11.3.0", |
| 292 | "targets": [ |
| 293 | { |
| 294 | "editorMode": "code", |
| 295 | "expr": "sum by (le, model_name) (rate(vllm:request_prompt_tokens_bucket{model_name=~\"$Deployment_id\"}[$__rate_interval]))", |
| 296 | "legendFormat": "{{model_name}} le={{le}}", |
| 297 | "range": true, |
| 298 | "refId": "A" |
| 299 | } |
| 300 | ], |
| 301 | "title": "Input Token Size Distribution", |
| 302 | "type": "histogram" |
| 303 | }, |
| 304 | { |
| 305 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 306 | "fieldConfig": { |
| 307 | "defaults": { |
| 308 | "color": { "mode": "thresholds" }, |
| 309 | "mappings": [ |
| 310 | { "options": { "calculation ": { "index": 0, "text": "Last (not null)" } }, "type": "value" } |
| 311 | ], |
| 312 | "thresholds": { |
| 313 | "mode": "absolute", |
| 314 | "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }] |
| 315 | }, |
| 316 | "unit": "cps" |
| 317 | }, |
| 318 | "overrides": [] |
| 319 | }, |
| 320 | "gridPos": { "h": 3, "w": 7, "x": 10, "y": 8 }, |
| 321 | "id": 9, |
| 322 | "options": { |
| 323 | "colorMode": "value", |
| 324 | "graphMode": "area", |
| 325 | "justifyMode": "auto", |
| 326 | "orientation": "auto", |
| 327 | "percentChangeColorMode": "standard", |
| 328 | "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, |
| 329 | "showPercentChange": false, |
| 330 | "textMode": "auto", |
| 331 | "wideLayout": true |
| 332 | }, |
| 333 | "pluginVersion": "11.3.0", |
| 334 | "targets": [ |
| 335 | { |
| 336 | "editorMode": "code", |
| 337 | "expr": "histogram_quantile(0.90, sum by(le, model_name) (rate(vllm:request_prompt_tokens_bucket{model_name=~\"$Deployment_id\"}[$__rate_interval])))", |
| 338 | "legendFormat": "__auto", |
| 339 | "range": true, |
| 340 | "refId": "A" |
| 341 | } |
| 342 | ], |
| 343 | "title": "Input Token Size p90", |
| 344 | "type": "stat" |
| 345 | }, |
| 346 | { |
| 347 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 348 | "fieldConfig": { |
| 349 | "defaults": { |
| 350 | "color": { "mode": "thresholds" }, |
| 351 | "mappings": [ |
| 352 | { "options": { "Calculation": { "index": 0, "text": "Last (not null)" } }, "type": "value" } |
| 353 | ], |
| 354 | "thresholds": { |
| 355 | "mode": "absolute", |
| 356 | "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }] |
| 357 | }, |
| 358 | "unit": "cps" |
| 359 | }, |
| 360 | "overrides": [] |
| 361 | }, |
| 362 | "gridPos": { "h": 3, "w": 7, "x": 17, "y": 8 }, |
| 363 | "id": 8, |
| 364 | "options": { |
| 365 | "colorMode": "value", |
| 366 | "graphMode": "area", |
| 367 | "justifyMode": "auto", |
| 368 | "orientation": "auto", |
| 369 | "percentChangeColorMode": "standard", |
| 370 | "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, |
| 371 | "showPercentChange": false, |
| 372 | "textMode": "auto", |
| 373 | "wideLayout": true |
| 374 | }, |
| 375 | "pluginVersion": "11.3.0", |
| 376 | "targets": [ |
| 377 | { |
| 378 | "editorMode": "code", |
| 379 | "expr": "histogram_quantile(0.50, sum by(le, model_name) (rate(vllm:request_prompt_tokens_bucket{model_name=~\"$Deployment_id\"}[$__rate_interval])))", |
| 380 | "legendFormat": "__auto", |
| 381 | "range": true, |
| 382 | "refId": "A" |
| 383 | } |
| 384 | ], |
| 385 | "title": "Input Token Size p50", |
| 386 | "type": "stat" |
| 387 | }, |
| 388 | { |
| 389 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 390 | "fieldConfig": { |
| 391 | "defaults": { |
| 392 | "color": { "mode": "thresholds" }, |
| 393 | "mappings": [ |
| 394 | { "options": { "Calcultaion": { "index": 0, "text": "mean" } }, "type": "value" } |
| 395 | ], |
| 396 | "thresholds": { |
| 397 | "mode": "absolute", |
| 398 | "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }] |
| 399 | }, |
| 400 | "unit": "cps" |
| 401 | }, |
| 402 | "overrides": [] |
| 403 | }, |
| 404 | "gridPos": { "h": 3, "w": 7, "x": 10, "y": 11 }, |
| 405 | "id": 7, |
| 406 | "options": { |
| 407 | "colorMode": "value", |
| 408 | "graphMode": "area", |
| 409 | "justifyMode": "auto", |
| 410 | "orientation": "auto", |
| 411 | "percentChangeColorMode": "standard", |
| 412 | "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, |
| 413 | "showPercentChange": false, |
| 414 | "textMode": "auto", |
| 415 | "wideLayout": true |
| 416 | }, |
| 417 | "pluginVersion": "11.3.0", |
| 418 | "targets": [ |
| 419 | { |
| 420 | "editorMode": "code", |
| 421 | "expr": "sum(rate(vllm:prompt_tokens_total{model_name=~\"$Deployment_id\"}[$__rate_interval]))\n/\nsum(rate(vllm:request_success_total{model_name=~\"$Deployment_id\"}[$__rate_interval]))", |
| 422 | "legendFormat": "__auto", |
| 423 | "range": true, |
| 424 | "refId": "A" |
| 425 | } |
| 426 | ], |
| 427 | "title": "Input Token Size Avg", |
| 428 | "type": "stat" |
| 429 | }, |
| 430 | { |
| 431 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 432 | "fieldConfig": { |
| 433 | "defaults": { |
| 434 | "color": { "mode": "thresholds" }, |
| 435 | "mappings": [ |
| 436 | { "options": { "Calculation": { "index": 0, "text": "Last (not null)" } }, "type": "value" } |
| 437 | ], |
| 438 | "thresholds": { |
| 439 | "mode": "absolute", |
| 440 | "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }] |
| 441 | }, |
| 442 | "unit": "cps" |
| 443 | }, |
| 444 | "overrides": [] |
| 445 | }, |
| 446 | "gridPos": { "h": 3, "w": 7, "x": 17, "y": 11 }, |
| 447 | "id": 10, |
| 448 | "options": { |
| 449 | "colorMode": "value", |
| 450 | "graphMode": "area", |
| 451 | "justifyMode": "auto", |
| 452 | "orientation": "auto", |
| 453 | "percentChangeColorMode": "standard", |
| 454 | "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, |
| 455 | "showPercentChange": false, |
| 456 | "textMode": "auto", |
| 457 | "wideLayout": true |
| 458 | }, |
| 459 | "pluginVersion": "11.3.0", |
| 460 | "targets": [ |
| 461 | { |
| 462 | "editorMode": "code", |
| 463 | "expr": "histogram_quantile(0.99, sum by(le, model_name) (rate(vllm:request_prompt_tokens_bucket{model_name=~\"$Deployment_id\"}[$__rate_interval])))", |
| 464 | "legendFormat": "__auto", |
| 465 | "range": true, |
| 466 | "refId": "A" |
| 467 | } |
| 468 | ], |
| 469 | "title": "Input Token Size p99", |
| 470 | "type": "stat" |
| 471 | }, |
| 472 | { |
| 473 | "collapsed": true, |
| 474 | "gridPos": { "h": 1, "w": 24, "x": 0, "y": 14 }, |
| 475 | "id": 18, |
| 476 | "panels": [], |
| 477 | "title": "Input Token Over Time", |
| 478 | "type": "row" |
| 479 | }, |
| 480 | { |
| 481 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 482 | "fieldConfig": { |
| 483 | "defaults": { |
| 484 | "color": { "mode": "palette-classic" }, |
| 485 | "custom": { |
| 486 | "axisBorderShow": false, |
| 487 | "axisCenteredZero": false, |
| 488 | "axisColorMode": "text", |
| 489 | "axisLabel": "", |
| 490 | "axisPlacement": "auto", |
| 491 | "barAlignment": 0, |
| 492 | "barWidthFactor": 0.6, |
| 493 | "drawStyle": "line", |
| 494 | "fillOpacity": 0, |
| 495 | "gradientMode": "none", |
| 496 | "hideFrom": { "legend": false, "tooltip": false, "viz": false }, |
| 497 | "insertNulls": false, |
| 498 | "lineInterpolation": "linear", |
| 499 | "lineWidth": 1, |
| 500 | "pointSize": 5, |
| 501 | "scaleDistribution": { "type": "linear" }, |
| 502 | "showPoints": "auto", |
| 503 | "spanNulls": false, |
| 504 | "stacking": { "group": "A", "mode": "none" }, |
| 505 | "thresholdsStyle": { "mode": "off" } |
| 506 | }, |
| 507 | "mappings": [], |
| 508 | "thresholds": { |
| 509 | "mode": "absolute", |
| 510 | "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }] |
| 511 | }, |
| 512 | "unit": "cps" |
| 513 | }, |
| 514 | "overrides": [] |
| 515 | }, |
| 516 | "gridPos": { "h": 6, "w": 10, "x": 0, "y": 15 }, |
| 517 | "id": 11, |
| 518 | "options": { |
| 519 | "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, |
| 520 | "tooltip": { "mode": "single", "sort": "none" } |
| 521 | }, |
| 522 | "pluginVersion": "11.3.0", |
| 523 | "targets": [ |
| 524 | { |
| 525 | "editorMode": "code", |
| 526 | "expr": "sum by (model_name) (rate(vllm:prompt_tokens_total{model_name=~\"$Deployment_id\"}[$__rate_interval]))", |
| 527 | "legendFormat": "{{model_name}}", |
| 528 | "range": true, |
| 529 | "refId": "A" |
| 530 | } |
| 531 | ], |
| 532 | "title": "Input Tokens Over Time", |
| 533 | "type": "timeseries" |
| 534 | }, |
| 535 | { |
| 536 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 537 | "fieldConfig": { |
| 538 | "defaults": { |
| 539 | "color": { "mode": "thresholds" }, |
| 540 | "mappings": [ |
| 541 | { "options": { "Calculation": { "index": 0, "text": "mean" } }, "type": "value" } |
| 542 | ], |
| 543 | "thresholds": { |
| 544 | "mode": "absolute", |
| 545 | "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }] |
| 546 | }, |
| 547 | "unit": "cps" |
| 548 | }, |
| 549 | "overrides": [] |
| 550 | }, |
| 551 | "gridPos": { "h": 3, "w": 7, "x": 10, "y": 15 }, |
| 552 | "id": 12, |
| 553 | "options": { |
| 554 | "colorMode": "value", |
| 555 | "graphMode": "area", |
| 556 | "justifyMode": "auto", |
| 557 | "orientation": "auto", |
| 558 | "percentChangeColorMode": "standard", |
| 559 | "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, |
| 560 | "showPercentChange": false, |
| 561 | "textMode": "auto", |
| 562 | "wideLayout": true |
| 563 | }, |
| 564 | "pluginVersion": "11.3.0", |
| 565 | "targets": [ |
| 566 | { |
| 567 | "editorMode": "code", |
| 568 | "expr": "sum(rate(vllm:prompt_tokens_total{model_name=~\"$Deployment_id\"}[$__rate_interval]))", |
| 569 | "legendFormat": "__auto", |
| 570 | "range": true, |
| 571 | "refId": "A" |
| 572 | } |
| 573 | ], |
| 574 | "title": "Input Tokens/Sec Avg", |
| 575 | "type": "stat" |
| 576 | }, |
| 577 | { |
| 578 | "collapsed": false, |
| 579 | "gridPos": { "h": 1, "w": 24, "x": 0, "y": 21 }, |
| 580 | "id": 17, |
| 581 | "panels": [], |
| 582 | "title": "Output Token Over Time", |
| 583 | "type": "row" |
| 584 | }, |
| 585 | { |
| 586 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 587 | "fieldConfig": { |
| 588 | "defaults": { |
| 589 | "color": { "mode": "palette-classic" }, |
| 590 | "custom": { |
| 591 | "axisBorderShow": false, |
| 592 | "axisCenteredZero": false, |
| 593 | "axisColorMode": "text", |
| 594 | "axisLabel": "", |
| 595 | "axisPlacement": "auto", |
| 596 | "barAlignment": 0, |
| 597 | "barWidthFactor": 0.6, |
| 598 | "drawStyle": "line", |
| 599 | "fillOpacity": 0, |
| 600 | "gradientMode": "none", |
| 601 | "hideFrom": { "legend": false, "tooltip": false, "viz": false }, |
| 602 | "insertNulls": false, |
| 603 | "lineInterpolation": "linear", |
| 604 | "lineWidth": 1, |
| 605 | "pointSize": 5, |
| 606 | "scaleDistribution": { "type": "linear" }, |
| 607 | "showPoints": "auto", |
| 608 | "spanNulls": false, |
| 609 | "stacking": { "group": "A", "mode": "none" }, |
| 610 | "thresholdsStyle": { "mode": "off" } |
| 611 | }, |
| 612 | "mappings": [], |
| 613 | "thresholds": { |
| 614 | "mode": "absolute", |
| 615 | "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }] |
| 616 | }, |
| 617 | "unit": "cps" |
| 618 | }, |
| 619 | "overrides": [] |
| 620 | }, |
| 621 | "gridPos": { "h": 6, "w": 10, "x": 0, "y": 22 }, |
| 622 | "id": 13, |
| 623 | "options": { |
| 624 | "legend": { "calcs": [], "displayMode": "list", "placement": "bottom", "showLegend": true }, |
| 625 | "tooltip": { "mode": "single", "sort": "none" } |
| 626 | }, |
| 627 | "pluginVersion": "11.3.0", |
| 628 | "targets": [ |
| 629 | { |
| 630 | "editorMode": "code", |
| 631 | "expr": "sum by (model_name) (rate(vllm:generation_tokens_total{model_name=~\"$Deployment_id\"}[$__rate_interval]))", |
| 632 | "legendFormat": "{{model_name}}", |
| 633 | "range": true, |
| 634 | "refId": "A" |
| 635 | } |
| 636 | ], |
| 637 | "title": "Output Tokens Over Time", |
| 638 | "type": "timeseries" |
| 639 | }, |
| 640 | { |
| 641 | "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, |
| 642 | "fieldConfig": { |
| 643 | "defaults": { |
| 644 | "color": { "mode": "thresholds" }, |
| 645 | "mappings": [ |
| 646 | { "options": { "Calculation": { "index": 0, "text": "mean" } }, "type": "value" } |
| 647 | ], |
| 648 | "thresholds": { |
| 649 | "mode": "absolute", |
| 650 | "steps": [{ "color": "green", "value": null }, { "color": "red", "value": 80 }] |
| 651 | }, |
| 652 | "unit": "cps" |
| 653 | }, |
| 654 | "overrides": [] |
| 655 | }, |
| 656 | "gridPos": { "h": 3, "w": 7, "x": 10, "y": 22 }, |
| 657 | "id": 14, |
| 658 | "options": { |
| 659 | "colorMode": "value", |
| 660 | "graphMode": "area", |
| 661 | "justifyMode": "auto", |
| 662 | "orientation": "auto", |
| 663 | "percentChangeColorMode": "standard", |
| 664 | "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, |
| 665 | "showPercentChange": false, |
| 666 | "textMode": "auto", |
| 667 | "wideLayout": true |
| 668 | }, |
| 669 | "pluginVersion": "11.3.0", |
| 670 | "targets": [ |
| 671 | { |
| 672 | "editorMode": "code", |
| 673 | "expr": "sum(rate(vllm:generation_tokens_total{model_name=~\"$Deployment_id\"}[$__rate_interval]))", |
| 674 | "legendFormat": "__auto", |
| 675 | "range": true, |
| 676 | "refId": "A" |
| 677 | } |
| 678 | ], |
| 679 | "title": "Output Tokens/Sec Avg", |
| 680 | "type": "stat" |
| 681 | } |
| 682 | ], |
| 683 | "preload": false, |
| 684 | "schemaVersion": 40, |
| 685 | "tags": [], |
| 686 | "templating": { |
| 687 | "list": [ |
| 688 | { |
| 689 | "current": { "text": "Prometheus", "value": "4184fc20-68a7-483a-8d9b-7caa59c680dd" }, |
| 690 | "label": "datasource", |
| 691 | "name": "DS_PROMETHEUS", |
| 692 | "options": [], |
| 693 | "query": "prometheus", |
| 694 | "refresh": 1, |
| 695 | "type": "datasource" |
| 696 | }, |
| 697 | { |
| 698 | "current": { "text": ["All"], "value": ["$__all"] }, |
| 699 | "definition": "label_values(vllm:request_success_total,model_name)", |
| 700 | "includeAll": true, |
| 701 | "label": "Deployment_ID", |
| 702 | "multi": true, |
| 703 | "name": "Deployment_id", |
| 704 | "options": [], |
| 705 | "query": { |
| 706 | "qryType": 1, |
| 707 | "query": "label_values(vllm:request_success_total,model_name)", |
| 708 | "refId": "PrometheusVariableQueryEditor-VariableQuery" |
| 709 | }, |
| 710 | "refresh": 1, |
| 711 | "regex": "", |
| 712 | "sort": 1, |
| 713 | "type": "query" |
| 714 | }, |
| 715 | { |
| 716 | "current": { "text": "All hours", "value": "All hours" }, |
| 717 | "hide": 2, |
| 718 | "label": "Rush Hours Only", |
| 719 | "name": "rush_hours", |
| 720 | "options": [ |
| 721 | { "selected": true, "text": "false", "value": "All hours" }, |
| 722 | { "selected": false, "text": "true", "value": "Rush hours" } |
| 723 | ], |
| 724 | "query": "false : All hours, true : Rush hours", |
| 725 | "type": "custom" |
| 726 | }, |
| 727 | { |
| 728 | "current": { "text": "All", "value": "All" }, |
| 729 | "hide": 2, |
| 730 | "label": "Rush Hours Type", |
| 731 | "name": "rush_hours_type", |
| 732 | "options": [ |
| 733 | { "selected": true, "text": "^All__.*$", "value": "All" }, |
| 734 | { "selected": false, "text": "^Static__.*$", "value": "Static" }, |
| 735 | { "selected": false, "text": "^Dynamic__.*$", "value": "Dynamic" } |
| 736 | ], |
| 737 | "query": "^All__.*$ : All, ^Static__.*$ : Static, ^Dynamic__.*$ : Dynamic", |
| 738 | "type": "custom" |
| 739 | }, |
| 740 | { |
| 741 | "current": { "text": "", "value": "" }, |
| 742 | "hide": 2, |
| 743 | "name": "query0", |
| 744 | "options": [], |
| 745 | "query": "", |
| 746 | "refresh": 1, |
| 747 | "regex": "", |
| 748 | "type": "query" |
| 749 | } |
| 750 | ] |
| 751 | }, |
| 752 | "time": { "from": "now-12h", "to": "now" }, |
| 753 | "timepicker": {}, |
| 754 | "timezone": "browser", |
| 755 | "title": "Query Statistics_New4", |
| 756 | "uid": "query-statistics4", |
| 757 | "version": 2, |
| 758 | "weekStart": "" |
| 759 | } |
| 760 |