| 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 | "editable": true, |
| 19 | "fiscalYearStartMonth": 0, |
| 20 | "graphTooltip": 0, |
| 21 | "id": 26, |
| 22 | "links": [], |
| 23 | "panels": [ |
| 24 | { |
| 25 | "collapsed": false, |
| 26 | "gridPos": { |
| 27 | "h": 1, |
| 28 | "w": 24, |
| 29 | "x": 0, |
| 30 | "y": 0 |
| 31 | }, |
| 32 | "id": 9, |
| 33 | "panels": [], |
| 34 | "title": "Graph: E2E latency over time ", |
| 35 | "type": "row" |
| 36 | }, |
| 37 | { |
| 38 | "datasource": { |
| 39 | "type": "prometheus", |
| 40 | "uid": "${DS_PROMETHEUS}" |
| 41 | }, |
| 42 | "description": "End-to-End latency of requests, showing average and key percentiles over time.", |
| 43 | "fieldConfig": { |
| 44 | "defaults": { |
| 45 | "color": { |
| 46 | "mode": "palette-classic" |
| 47 | }, |
| 48 | "custom": { |
| 49 | "axisBorderShow": false, |
| 50 | "axisCenteredZero": false, |
| 51 | "axisColorMode": "text", |
| 52 | "axisLabel": "Latency", |
| 53 | "axisPlacement": "auto", |
| 54 | "barAlignment": 0, |
| 55 | "barWidthFactor": 0.6, |
| 56 | "drawStyle": "line", |
| 57 | "fillOpacity": 18, |
| 58 | "gradientMode": "none", |
| 59 | "hideFrom": { |
| 60 | "legend": false, |
| 61 | "tooltip": false, |
| 62 | "viz": false |
| 63 | }, |
| 64 | "insertNulls": false, |
| 65 | "lineInterpolation": "linear", |
| 66 | "lineWidth": 1, |
| 67 | "pointSize": 5, |
| 68 | "scaleDistribution": { |
| 69 | "type": "linear" |
| 70 | }, |
| 71 | "showPoints": "auto", |
| 72 | "spanNulls": true, |
| 73 | "stacking": { |
| 74 | "group": "A", |
| 75 | "mode": "none" |
| 76 | }, |
| 77 | "thresholdsStyle": { |
| 78 | "mode": "off" |
| 79 | } |
| 80 | }, |
| 81 | "decimals": 2, |
| 82 | "mappings": [], |
| 83 | "thresholds": { |
| 84 | "mode": "absolute", |
| 85 | "steps": [ |
| 86 | { |
| 87 | "color": "green", |
| 88 | "value": null |
| 89 | }, |
| 90 | { |
| 91 | "color": "red", |
| 92 | "value": 80 |
| 93 | } |
| 94 | ] |
| 95 | }, |
| 96 | "unit": "s" |
| 97 | }, |
| 98 | "overrides": [] |
| 99 | }, |
| 100 | "gridPos": { |
| 101 | "h": 8, |
| 102 | "w": 12, |
| 103 | "x": 0, |
| 104 | "y": 1 |
| 105 | }, |
| 106 | "id": 1, |
| 107 | "options": { |
| 108 | "legend": { |
| 109 | "calcs": [], |
| 110 | "displayMode": "list", |
| 111 | "placement": "bottom", |
| 112 | "showLegend": true |
| 113 | }, |
| 114 | "tooltip": { |
| 115 | "mode": "single", |
| 116 | "sort": "none" |
| 117 | } |
| 118 | }, |
| 119 | "pluginVersion": "11.3.0", |
| 120 | "targets": [ |
| 121 | { |
| 122 | "datasource": { |
| 123 | "type": "prometheus", |
| 124 | "uid": "${DS_PROMETHEUS}" |
| 125 | }, |
| 126 | "editorMode": "code", |
| 127 | "expr": "rate(vllm:e2e_request_latency_seconds_sum[$__interval]) / rate(vllm:e2e_request_latency_seconds_count[$__interval])", |
| 128 | "format": "table", |
| 129 | "legendFormat": "E2E Latency", |
| 130 | "range": true, |
| 131 | "refId": "A" |
| 132 | } |
| 133 | ], |
| 134 | "title": "E2E Latency over Time", |
| 135 | "type": "timeseries" |
| 136 | }, |
| 137 | { |
| 138 | "datasource": { |
| 139 | "type": "prometheus", |
| 140 | "uid": "${DS_PROMETHEUS}" |
| 141 | }, |
| 142 | "description": "99th percentile of End-to-End request latency over the selected time range.", |
| 143 | "fieldConfig": { |
| 144 | "defaults": { |
| 145 | "color": { |
| 146 | "mode": "thresholds" |
| 147 | }, |
| 148 | "decimals": 2, |
| 149 | "displayName": "P99", |
| 150 | "mappings": [], |
| 151 | "thresholds": { |
| 152 | "mode": "absolute", |
| 153 | "steps": [ |
| 154 | { |
| 155 | "color": "green", |
| 156 | "value": null |
| 157 | }, |
| 158 | { |
| 159 | "color": "red", |
| 160 | "value": 80 |
| 161 | } |
| 162 | ] |
| 163 | }, |
| 164 | "unit": "s" |
| 165 | }, |
| 166 | "overrides": [] |
| 167 | }, |
| 168 | "gridPos": { |
| 169 | "h": 4, |
| 170 | "w": 6, |
| 171 | "x": 12, |
| 172 | "y": 1 |
| 173 | }, |
| 174 | "id": 5, |
| 175 | "options": { |
| 176 | "colorMode": "value", |
| 177 | "graphMode": "area", |
| 178 | "justifyMode": "auto", |
| 179 | "orientation": "auto", |
| 180 | "percentChangeColorMode": "standard", |
| 181 | "reduceOptions": { |
| 182 | "calcs": [ |
| 183 | "lastNotNull" |
| 184 | ], |
| 185 | "fields": "", |
| 186 | "values": false |
| 187 | }, |
| 188 | "showPercentChange": false, |
| 189 | "textMode": "auto", |
| 190 | "wideLayout": true |
| 191 | }, |
| 192 | "pluginVersion": "11.3.0", |
| 193 | "targets": [ |
| 194 | { |
| 195 | "editorMode": "code", |
| 196 | "expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:e2e_request_latency_seconds_bucket[$__range])))", |
| 197 | "legendFormat": "__auto", |
| 198 | "range": true, |
| 199 | "refId": "A" |
| 200 | } |
| 201 | ], |
| 202 | "title": "E2E Latency (P99)", |
| 203 | "type": "stat" |
| 204 | }, |
| 205 | { |
| 206 | "datasource": { |
| 207 | "type": "prometheus", |
| 208 | "uid": "${DS_PROMETHEUS}" |
| 209 | }, |
| 210 | "description": "90th percentile of End-to-End request latency over the selected time range.", |
| 211 | "fieldConfig": { |
| 212 | "defaults": { |
| 213 | "color": { |
| 214 | "mode": "thresholds" |
| 215 | }, |
| 216 | "decimals": 2, |
| 217 | "displayName": "P90", |
| 218 | "mappings": [], |
| 219 | "thresholds": { |
| 220 | "mode": "absolute", |
| 221 | "steps": [ |
| 222 | { |
| 223 | "color": "green", |
| 224 | "value": null |
| 225 | }, |
| 226 | { |
| 227 | "color": "red", |
| 228 | "value": 80 |
| 229 | } |
| 230 | ] |
| 231 | }, |
| 232 | "unit": "s" |
| 233 | }, |
| 234 | "overrides": [] |
| 235 | }, |
| 236 | "gridPos": { |
| 237 | "h": 4, |
| 238 | "w": 6, |
| 239 | "x": 18, |
| 240 | "y": 1 |
| 241 | }, |
| 242 | "id": 4, |
| 243 | "options": { |
| 244 | "colorMode": "value", |
| 245 | "graphMode": "area", |
| 246 | "justifyMode": "auto", |
| 247 | "orientation": "auto", |
| 248 | "percentChangeColorMode": "standard", |
| 249 | "reduceOptions": { |
| 250 | "calcs": [ |
| 251 | "lastNotNull" |
| 252 | ], |
| 253 | "fields": "", |
| 254 | "values": false |
| 255 | }, |
| 256 | "showPercentChange": false, |
| 257 | "textMode": "auto", |
| 258 | "wideLayout": true |
| 259 | }, |
| 260 | "pluginVersion": "11.3.0", |
| 261 | "targets": [ |
| 262 | { |
| 263 | "editorMode": "code", |
| 264 | "expr": "histogram_quantile(0.90, sum by(le) (rate(vllm:e2e_request_latency_seconds_bucket[$__range])))", |
| 265 | "legendFormat": "__auto", |
| 266 | "range": true, |
| 267 | "refId": "A" |
| 268 | } |
| 269 | ], |
| 270 | "title": "E2E Latency (P90)", |
| 271 | "type": "stat" |
| 272 | }, |
| 273 | { |
| 274 | "datasource": { |
| 275 | "type": "prometheus", |
| 276 | "uid": "${DS_PROMETHEUS}" |
| 277 | }, |
| 278 | "description": "Average End-to-End request latency over the selected time range.", |
| 279 | "fieldConfig": { |
| 280 | "defaults": { |
| 281 | "color": { |
| 282 | "mode": "thresholds" |
| 283 | }, |
| 284 | "decimals": 2, |
| 285 | "displayName": "Average", |
| 286 | "mappings": [], |
| 287 | "thresholds": { |
| 288 | "mode": "absolute", |
| 289 | "steps": [ |
| 290 | { |
| 291 | "color": "green", |
| 292 | "value": null |
| 293 | }, |
| 294 | { |
| 295 | "color": "red", |
| 296 | "value": 80 |
| 297 | } |
| 298 | ] |
| 299 | }, |
| 300 | "unit": "s" |
| 301 | }, |
| 302 | "overrides": [] |
| 303 | }, |
| 304 | "gridPos": { |
| 305 | "h": 4, |
| 306 | "w": 6, |
| 307 | "x": 12, |
| 308 | "y": 5 |
| 309 | }, |
| 310 | "id": 2, |
| 311 | "options": { |
| 312 | "colorMode": "value", |
| 313 | "graphMode": "area", |
| 314 | "justifyMode": "auto", |
| 315 | "orientation": "auto", |
| 316 | "percentChangeColorMode": "standard", |
| 317 | "reduceOptions": { |
| 318 | "calcs": [ |
| 319 | "lastNotNull" |
| 320 | ], |
| 321 | "fields": "", |
| 322 | "values": false |
| 323 | }, |
| 324 | "showPercentChange": false, |
| 325 | "textMode": "auto", |
| 326 | "wideLayout": true |
| 327 | }, |
| 328 | "pluginVersion": "11.3.0", |
| 329 | "targets": [ |
| 330 | { |
| 331 | "editorMode": "code", |
| 332 | "expr": "(sum(increase(vllm:e2e_request_latency_seconds_sum[$__range])) / sum(increase(vllm:e2e_request_latency_seconds_count[$__range])))", |
| 333 | "legendFormat": "Average E2E Latency", |
| 334 | "range": true, |
| 335 | "refId": "A" |
| 336 | } |
| 337 | ], |
| 338 | "title": "E2E Latency (Avg)", |
| 339 | "type": "stat" |
| 340 | }, |
| 341 | { |
| 342 | "datasource": { |
| 343 | "type": "prometheus", |
| 344 | "uid": "${DS_PROMETHEUS}" |
| 345 | }, |
| 346 | "description": "50th percentile (median) of End-to-End request latency over the selected time range.", |
| 347 | "fieldConfig": { |
| 348 | "defaults": { |
| 349 | "color": { |
| 350 | "mode": "thresholds" |
| 351 | }, |
| 352 | "decimals": 2, |
| 353 | "displayName": "P50", |
| 354 | "mappings": [], |
| 355 | "thresholds": { |
| 356 | "mode": "absolute", |
| 357 | "steps": [ |
| 358 | { |
| 359 | "color": "green", |
| 360 | "value": null |
| 361 | }, |
| 362 | { |
| 363 | "color": "red", |
| 364 | "value": 80 |
| 365 | } |
| 366 | ] |
| 367 | }, |
| 368 | "unit": "s" |
| 369 | }, |
| 370 | "overrides": [] |
| 371 | }, |
| 372 | "gridPos": { |
| 373 | "h": 4, |
| 374 | "w": 6, |
| 375 | "x": 18, |
| 376 | "y": 5 |
| 377 | }, |
| 378 | "id": 3, |
| 379 | "options": { |
| 380 | "colorMode": "value", |
| 381 | "graphMode": "area", |
| 382 | "justifyMode": "auto", |
| 383 | "orientation": "auto", |
| 384 | "percentChangeColorMode": "standard", |
| 385 | "reduceOptions": { |
| 386 | "calcs": [ |
| 387 | "lastNotNull" |
| 388 | ], |
| 389 | "fields": "", |
| 390 | "values": false |
| 391 | }, |
| 392 | "showPercentChange": false, |
| 393 | "textMode": "auto", |
| 394 | "wideLayout": true |
| 395 | }, |
| 396 | "pluginVersion": "11.3.0", |
| 397 | "targets": [ |
| 398 | { |
| 399 | "editorMode": "code", |
| 400 | "expr": "histogram_quantile(0.50, sum by(le) (rate(vllm:e2e_request_latency_seconds_bucket[$__range])))", |
| 401 | "legendFormat": "__auto", |
| 402 | "range": true, |
| 403 | "refId": "A" |
| 404 | } |
| 405 | ], |
| 406 | "title": "E2E Latency (P50)", |
| 407 | "type": "stat" |
| 408 | }, |
| 409 | { |
| 410 | "collapsed": false, |
| 411 | "gridPos": { |
| 412 | "h": 1, |
| 413 | "w": 24, |
| 414 | "x": 0, |
| 415 | "y": 9 |
| 416 | }, |
| 417 | "id": 8, |
| 418 | "panels": [], |
| 419 | "title": "Graph: TTFT(Time To First Token) over time ", |
| 420 | "type": "row" |
| 421 | }, |
| 422 | { |
| 423 | "datasource": { |
| 424 | "type": "prometheus", |
| 425 | "uid": "${DS_PROMETHEUS}" |
| 426 | }, |
| 427 | "description": "Time to first token (TTFT) latency, showing average and key percentiles over time.", |
| 428 | "fieldConfig": { |
| 429 | "defaults": { |
| 430 | "color": { |
| 431 | "mode": "palette-classic" |
| 432 | }, |
| 433 | "custom": { |
| 434 | "axisBorderShow": false, |
| 435 | "axisCenteredZero": false, |
| 436 | "axisColorMode": "text", |
| 437 | "axisLabel": "Latency", |
| 438 | "axisPlacement": "auto", |
| 439 | "barAlignment": 0, |
| 440 | "barWidthFactor": 0.6, |
| 441 | "drawStyle": "line", |
| 442 | "fillOpacity": 18, |
| 443 | "gradientMode": "none", |
| 444 | "hideFrom": { |
| 445 | "legend": false, |
| 446 | "tooltip": false, |
| 447 | "viz": false |
| 448 | }, |
| 449 | "insertNulls": false, |
| 450 | "lineInterpolation": "linear", |
| 451 | "lineWidth": 1, |
| 452 | "pointSize": 5, |
| 453 | "scaleDistribution": { |
| 454 | "type": "linear" |
| 455 | }, |
| 456 | "showPoints": "auto", |
| 457 | "spanNulls": false, |
| 458 | "stacking": { |
| 459 | "group": "A", |
| 460 | "mode": "none" |
| 461 | }, |
| 462 | "thresholdsStyle": { |
| 463 | "mode": "off" |
| 464 | } |
| 465 | }, |
| 466 | "decimals": 2, |
| 467 | "mappings": [], |
| 468 | "thresholds": { |
| 469 | "mode": "absolute", |
| 470 | "steps": [ |
| 471 | { |
| 472 | "color": "green", |
| 473 | "value": null |
| 474 | }, |
| 475 | { |
| 476 | "color": "red", |
| 477 | "value": 80 |
| 478 | } |
| 479 | ] |
| 480 | }, |
| 481 | "unit": "s" |
| 482 | }, |
| 483 | "overrides": [] |
| 484 | }, |
| 485 | "gridPos": { |
| 486 | "h": 8, |
| 487 | "w": 12, |
| 488 | "x": 0, |
| 489 | "y": 10 |
| 490 | }, |
| 491 | "id": 10, |
| 492 | "options": { |
| 493 | "legend": { |
| 494 | "calcs": [], |
| 495 | "displayMode": "list", |
| 496 | "placement": "bottom", |
| 497 | "showLegend": true |
| 498 | }, |
| 499 | "tooltip": { |
| 500 | "mode": "single", |
| 501 | "sort": "none" |
| 502 | } |
| 503 | }, |
| 504 | "pluginVersion": "11.3.0", |
| 505 | "targets": [ |
| 506 | { |
| 507 | "editorMode": "code", |
| 508 | "expr": "rate(vllm:time_to_first_token_seconds_sum[$__interval]) / rate(vllm:time_to_first_token_seconds_count[$__interval])", |
| 509 | "format": "table", |
| 510 | "legendFormat": "TTFT (Avg)", |
| 511 | "range": true, |
| 512 | "refId": "A" |
| 513 | } |
| 514 | ], |
| 515 | "title": "TTFT Over Time", |
| 516 | "type": "timeseries" |
| 517 | }, |
| 518 | { |
| 519 | "datasource": { |
| 520 | "type": "prometheus", |
| 521 | "uid": "${DS_PROMETHEUS}" |
| 522 | }, |
| 523 | "description": "99th percentile of Time To First Token latency over the selected time range.", |
| 524 | "fieldConfig": { |
| 525 | "defaults": { |
| 526 | "color": { |
| 527 | "mode": "thresholds" |
| 528 | }, |
| 529 | "decimals": 2, |
| 530 | "displayName": "P99", |
| 531 | "mappings": [], |
| 532 | "thresholds": { |
| 533 | "mode": "absolute", |
| 534 | "steps": [ |
| 535 | { |
| 536 | "color": "green", |
| 537 | "value": null |
| 538 | }, |
| 539 | { |
| 540 | "color": "red", |
| 541 | "value": 80 |
| 542 | } |
| 543 | ] |
| 544 | }, |
| 545 | "unit": "s" |
| 546 | }, |
| 547 | "overrides": [] |
| 548 | }, |
| 549 | "gridPos": { |
| 550 | "h": 4, |
| 551 | "w": 6, |
| 552 | "x": 12, |
| 553 | "y": 10 |
| 554 | }, |
| 555 | "id": 14, |
| 556 | "options": { |
| 557 | "colorMode": "value", |
| 558 | "graphMode": "area", |
| 559 | "justifyMode": "auto", |
| 560 | "orientation": "auto", |
| 561 | "percentChangeColorMode": "standard", |
| 562 | "reduceOptions": { |
| 563 | "calcs": [ |
| 564 | "lastNotNull" |
| 565 | ], |
| 566 | "fields": "", |
| 567 | "values": false |
| 568 | }, |
| 569 | "showPercentChange": false, |
| 570 | "textMode": "auto", |
| 571 | "wideLayout": true |
| 572 | }, |
| 573 | "pluginVersion": "11.3.0", |
| 574 | "targets": [ |
| 575 | { |
| 576 | "editorMode": "code", |
| 577 | "expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:time_to_first_token_seconds_bucket[$__range])))", |
| 578 | "legendFormat": "TTFT (p99)", |
| 579 | "range": true, |
| 580 | "refId": "A" |
| 581 | } |
| 582 | ], |
| 583 | "title": "TTFT (P99)", |
| 584 | "type": "stat" |
| 585 | }, |
| 586 | { |
| 587 | "datasource": { |
| 588 | "type": "prometheus", |
| 589 | "uid": "${DS_PROMETHEUS}" |
| 590 | }, |
| 591 | "description": "90th percentile of Time To First Token latency over the selected time range.", |
| 592 | "fieldConfig": { |
| 593 | "defaults": { |
| 594 | "color": { |
| 595 | "mode": "thresholds" |
| 596 | }, |
| 597 | "decimals": 2, |
| 598 | "displayName": "P90", |
| 599 | "mappings": [], |
| 600 | "thresholds": { |
| 601 | "mode": "absolute", |
| 602 | "steps": [ |
| 603 | { |
| 604 | "color": "green", |
| 605 | "value": null |
| 606 | }, |
| 607 | { |
| 608 | "color": "red", |
| 609 | "value": 80 |
| 610 | } |
| 611 | ] |
| 612 | }, |
| 613 | "unit": "s" |
| 614 | }, |
| 615 | "overrides": [] |
| 616 | }, |
| 617 | "gridPos": { |
| 618 | "h": 4, |
| 619 | "w": 6, |
| 620 | "x": 18, |
| 621 | "y": 10 |
| 622 | }, |
| 623 | "id": 13, |
| 624 | "options": { |
| 625 | "colorMode": "value", |
| 626 | "graphMode": "area", |
| 627 | "justifyMode": "auto", |
| 628 | "orientation": "auto", |
| 629 | "percentChangeColorMode": "standard", |
| 630 | "reduceOptions": { |
| 631 | "calcs": [ |
| 632 | "lastNotNull" |
| 633 | ], |
| 634 | "fields": "", |
| 635 | "values": false |
| 636 | }, |
| 637 | "showPercentChange": false, |
| 638 | "textMode": "auto", |
| 639 | "wideLayout": true |
| 640 | }, |
| 641 | "pluginVersion": "11.3.0", |
| 642 | "targets": [ |
| 643 | { |
| 644 | "editorMode": "code", |
| 645 | "expr": "histogram_quantile(0.90, sum by(le) (rate(vllm:time_to_first_token_seconds_bucket[$__range])))", |
| 646 | "legendFormat": "TTFT (p90)", |
| 647 | "range": true, |
| 648 | "refId": "A" |
| 649 | } |
| 650 | ], |
| 651 | "title": "TTFT (P90)", |
| 652 | "type": "stat" |
| 653 | }, |
| 654 | { |
| 655 | "datasource": { |
| 656 | "type": "prometheus", |
| 657 | "uid": "${DS_PROMETHEUS}" |
| 658 | }, |
| 659 | "description": "Average Time To First Token latency over the selected time range.", |
| 660 | "fieldConfig": { |
| 661 | "defaults": { |
| 662 | "color": { |
| 663 | "mode": "thresholds" |
| 664 | }, |
| 665 | "decimals": 2, |
| 666 | "displayName": "Average", |
| 667 | "mappings": [], |
| 668 | "thresholds": { |
| 669 | "mode": "absolute", |
| 670 | "steps": [ |
| 671 | { |
| 672 | "color": "green", |
| 673 | "value": null |
| 674 | }, |
| 675 | { |
| 676 | "color": "red", |
| 677 | "value": 80 |
| 678 | } |
| 679 | ] |
| 680 | }, |
| 681 | "unit": "s" |
| 682 | }, |
| 683 | "overrides": [] |
| 684 | }, |
| 685 | "gridPos": { |
| 686 | "h": 4, |
| 687 | "w": 6, |
| 688 | "x": 12, |
| 689 | "y": 14 |
| 690 | }, |
| 691 | "id": 11, |
| 692 | "options": { |
| 693 | "colorMode": "value", |
| 694 | "graphMode": "area", |
| 695 | "justifyMode": "auto", |
| 696 | "orientation": "auto", |
| 697 | "percentChangeColorMode": "standard", |
| 698 | "reduceOptions": { |
| 699 | "calcs": [ |
| 700 | "lastNotNull" |
| 701 | ], |
| 702 | "fields": "", |
| 703 | "values": false |
| 704 | }, |
| 705 | "showPercentChange": false, |
| 706 | "textMode": "auto", |
| 707 | "wideLayout": true |
| 708 | }, |
| 709 | "pluginVersion": "11.3.0", |
| 710 | "targets": [ |
| 711 | { |
| 712 | "editorMode": "code", |
| 713 | "expr": "(sum(increase(vllm:time_to_first_token_seconds_sum[$__range])) / sum(increase(vllm:time_to_first_token_seconds_count[$__range])))", |
| 714 | "legendFormat": "__auto", |
| 715 | "range": true, |
| 716 | "refId": "A" |
| 717 | } |
| 718 | ], |
| 719 | "title": "TTFT (Avg)", |
| 720 | "type": "stat" |
| 721 | }, |
| 722 | { |
| 723 | "datasource": { |
| 724 | "type": "prometheus", |
| 725 | "uid": "${DS_PROMETHEUS}" |
| 726 | }, |
| 727 | "description": "50th percentile (median) of Time To First Token latency over the selected time range.", |
| 728 | "fieldConfig": { |
| 729 | "defaults": { |
| 730 | "color": { |
| 731 | "mode": "thresholds" |
| 732 | }, |
| 733 | "displayName": "P50", |
| 734 | "mappings": [], |
| 735 | "thresholds": { |
| 736 | "mode": "absolute", |
| 737 | "steps": [ |
| 738 | { |
| 739 | "color": "green", |
| 740 | "value": null |
| 741 | }, |
| 742 | { |
| 743 | "color": "red", |
| 744 | "value": 80 |
| 745 | } |
| 746 | ] |
| 747 | }, |
| 748 | "unit": "s" |
| 749 | }, |
| 750 | "overrides": [] |
| 751 | }, |
| 752 | "gridPos": { |
| 753 | "h": 4, |
| 754 | "w": 6, |
| 755 | "x": 18, |
| 756 | "y": 14 |
| 757 | }, |
| 758 | "id": 12, |
| 759 | "options": { |
| 760 | "colorMode": "value", |
| 761 | "graphMode": "area", |
| 762 | "justifyMode": "auto", |
| 763 | "orietitletChangeColorMode": "standard", |
| 764 | "reduceOptions": { |
| 765 | "calcs": [ |
| 766 | "lastNotNull" |
| 767 | ], |
| 768 | "fields": "", |
| 769 | "values": false |
| 770 | }, |
| 771 | "showPercentChange": false, |
| 772 | "textMode": "auto", |
| 773 | "wideLayout": true |
| 774 | }, |
| 775 | "pluginVersion": "11.3.0", |
| 776 | "targets": [ |
| 777 | { |
| 778 | "editorMode": "code", |
| 779 | "expr": "histogram_quantile(0.50, sum by(le) (rate(vllm:time_to_first_token_seconds_bucket[$__range])))", |
| 780 | "legendFormat": "__auto", |
| 781 | "range": true, |
| 782 | "refId": "A" |
| 783 | } |
| 784 | ], |
| 785 | "title": "TTFT (P50)", |
| 786 | "type": "stat" |
| 787 | }, |
| 788 | { |
| 789 | "collapsed": false, |
| 790 | "gridPos": { |
| 791 | "h": 1, |
| 792 | "w": 24, |
| 793 | "x": 0, |
| 794 | "y": 18 |
| 795 | }, |
| 796 | "id": 7, |
| 797 | "panels": [], |
| 798 | "title": "ITL (Iteration Latency / Time Per Output Token) over time.", |
| 799 | "type": "row" |
| 800 | }, |
| 801 | { |
| 802 | "datasource": { |
| 803 | "type": "prometheus", |
| 804 | "uid": "${DS_PROMETHEUS}" |
| 805 | }, |
| 806 | "description": "Iteration latency, or average time taken to generate a single output token, with percentiles.", |
| 807 | "fieldConfig": { |
| 808 | "defaults": { |
| 809 | "color": { |
| 810 | "mode": "palette-classic" |
| 811 | }, |
| 812 | "custom": { |
| 813 | "axisBorderShow": false, |
| 814 | "axisCenteredZero": false, |
| 815 | "axisColorMode": "text", |
| 816 | "axisLabel": "Latency", |
| 817 | "axisPlacement": "auto", |
| 818 | "barAlignment": 0, |
| 819 | "barWidthFactor": 0.6, |
| 820 | "drawStyle": "line", |
| 821 | "fillOpacity": 17, |
| 822 | "gradientMode": "none", |
| 823 | "hideFrom": { |
| 824 | "legend": false, |
| 825 | "tooltip": false, |
| 826 | "viz": false |
| 827 | }, |
| 828 | "insertNulls": false, |
| 829 | "lineInterpolation": "linear", |
| 830 | "lineWidth": 1, |
| 831 | "pointSize": 5, |
| 832 | "scaleDistribution": { |
| 833 | "type": "linear" |
| 834 | }, |
| 835 | "showPoints": "auto", |
| 836 | "spanNulls": false, |
| 837 | "stacking": { |
| 838 | "group": "A", |
| 839 | "mode": "none" |
| 840 | }, |
| 841 | "thresholdsStyle": { |
| 842 | "mode": "off" |
| 843 | } |
| 844 | }, |
| 845 | "decimals": 2, |
| 846 | "mappings": [], |
| 847 | "thresholds": { |
| 848 | "mode": "absolute", |
| 849 | "steps": [ |
| 850 | { |
| 851 | "color": "green", |
| 852 | "value": null |
| 853 | }, |
| 854 | { |
| 855 | "color": "red", |
| 856 | "value": 80 |
| 857 | } |
| 858 | ] |
| 859 | }, |
| 860 | "unit": "s" |
| 861 | }, |
| 862 | "overrides": [] |
| 863 | }, |
| 864 | "gridPos": { |
| 865 | "h": 8, |
| 866 | "w": 12, |
| 867 | "x": 0, |
| 868 | "y": 19 |
| 869 | }, |
| 870 | "id": 15, |
| 871 | "options": { |
| 872 | "legend": { |
| 873 | "calcs": [], |
| 874 | "displayMode": "list", |
| 875 | "placement": "bottom", |
| 876 | "showLegend": true |
| 877 | }, |
| 878 | "tooltip": { |
| 879 | "mode": "single", |
| 880 | "sort": "none" |
| 881 | } |
| 882 | }, |
| 883 | "pluginVersion": "11.3.0", |
| 884 | "targets": [ |
| 885 | { |
| 886 | "editorMode": "code", |
| 887 | "expr": "rate(vllm:inter_token_latency_seconds_sum[$__interval]) / rate(vllm:inter_token_latency_seconds_count[$__interval])", |
| 888 | "legendFormat": "ITL (Avg)", |
| 889 | "range": true, |
| 890 | "refId": "A" |
| 891 | }, |
| 892 | { |
| 893 | "datasource": { |
| 894 | "type": "prometheus", |
| 895 | "uid": "${DS_PROMETHEUS}" |
| 896 | }, |
| 897 | "editorMode": "code", |
| 898 | "expr": "histogram_quantile(0.50, sum by(le) (rate(vllm:inter_token_latency_seconds_bucket[$__interval])))", |
| 899 | "hide": false, |
| 900 | "instant": false, |
| 901 | "legendFormat": "ITL (p50)", |
| 902 | "range": true, |
| 903 | "refId": "B" |
| 904 | }, |
| 905 | { |
| 906 | "datasource": { |
| 907 | "type": "prometheus", |
| 908 | "uid": "${DS_PROMETHEUS}" |
| 909 | }, |
| 910 | "editorMode": "code", |
| 911 | "expr": "histogram_quantile(0.90, sum by(le) (rate(vllm:inter_token_latency_seconds_bucket[$__interval])))", |
| 912 | "hide": false, |
| 913 | "instant": false, |
| 914 | "legendFormat": "ITL (p90)", |
| 915 | "range": true, |
| 916 | "refId": "C" |
| 917 | }, |
| 918 | { |
| 919 | "datasource": { |
| 920 | "type": "prometheus", |
| 921 | "uid": "${DS_PROMETHEUS}" |
| 922 | }, |
| 923 | "editorMode": "code", |
| 924 | "expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:inter_token_latency_seconds_bucket[$__interval])))", |
| 925 | "hide": false, |
| 926 | "instant": false, |
| 927 | "legendFormat": "ITL (p99)", |
| 928 | "range": true, |
| 929 | "refId": "D" |
| 930 | } |
| 931 | ], |
| 932 | "title": "ITL (Time Per Output Token) Over Time", |
| 933 | "type": "timeseries" |
| 934 | }, |
| 935 | { |
| 936 | "datasource": { |
| 937 | "type": "prometheus", |
| 938 | "uid": "${DS_PROMETHEUS}" |
| 939 | }, |
| 940 | "description": "90th percentile of Iteration Latency over the selected time range.", |
| 941 | "fieldConfig": { |
| 942 | "defaults": { |
| 943 | "color": { |
| 944 | "mode": "thresholds" |
| 945 | }, |
| 946 | "decimals": 2, |
| 947 | "mappings": [], |
| 948 | "thresholds": { |
| 949 | "mode": "absolute", |
| 950 | "steps": [ |
| 951 | { |
| 952 | "color": "green", |
| 953 | "value": null |
| 954 | }, |
| 955 | { |
| 956 | "color": "red", |
| 957 | "value": 80 |
| 958 | } |
| 959 | ] |
| 960 | }, |
| 961 | "unit": "s" |
| 962 | }, |
| 963 | "overrides": [] |
| 964 | }, |
| 965 | "gridPos": { |
| 966 | "h": 4, |
| 967 | "w": 6, |
| 968 | "x": 12, |
| 969 | "y": 19 |
| 970 | }, |
| 971 | "id": 18, |
| 972 | "options": { |
| 973 | "colorMode": "value", |
| 974 | "graphMode": "area", |
| 975 | "justifyMode": "auto", |
| 976 | "orientation": "auto", |
| 977 | "percentChangeColorMode": "standard", |
| 978 | "reduceOptions": { |
| 979 | "calcs": [ |
| 980 | "lastNotNull" |
| 981 | ], |
| 982 | "fields": "", |
| 983 | "values": false |
| 984 | }, |
| 985 | "showPercentChange": false, |
| 986 | "textMode": "auto", |
| 987 | "wideLayout": true |
| 988 | }, |
| 989 | "pluginVersion": "11.3.0", |
| 990 | "targets": [ |
| 991 | { |
| 992 | "editorMode": "code", |
| 993 | "expr": "histogram_quantile(0.90, sum by(le) (rate(vllm:inter_token_latency_seconds_bucket[$__range])))", |
| 994 | "legendFormat": "__auto", |
| 995 | "range": true, |
| 996 | "refId": "A" |
| 997 | } |
| 998 | ], |
| 999 | "title": "ITL (P90)", |
| 1000 | "type": "stat" |
| 1001 | }, |
| 1002 | { |
| 1003 | "datasource": { |
| 1004 | "type": "prometheus", |
| 1005 | "uid": "${DS_PROMETHEUS}" |
| 1006 | }, |
| 1007 | "description": "99th percentile of Iteration Latency over the selected time range.\n\n", |
| 1008 | "fieldConfig": { |
| 1009 | "defaults": { |
| 1010 | "color": { |
| 1011 | "mode": "thresholds" |
| 1012 | }, |
| 1013 | "decimals": 2, |
| 1014 | "mappings": [], |
| 1015 | "thresholds": { |
| 1016 | "mode": "absolute", |
| 1017 | "steps": [ |
| 1018 | { |
| 1019 | "color": "green", |
| 1020 | "value": null |
| 1021 | }, |
| 1022 | { |
| 1023 | "color": "red", |
| 1024 | "value": 80 |
| 1025 | } |
| 1026 | ] |
| 1027 | }, |
| 1028 | "unit": "s" |
| 1029 | }, |
| 1030 | "overrides": [] |
| 1031 | }, |
| 1032 | "gridPos": { |
| 1033 | "h": 4, |
| 1034 | "w": 6, |
| 1035 | "x": 18, |
| 1036 | "y": 19 |
| 1037 | }, |
| 1038 | "id": 19, |
| 1039 | "options": { |
| 1040 | "colorMode": "value", |
| 1041 | "graphMode": "area", |
| 1042 | "justifyMode": "auto", |
| 1043 | "orientation": "auto", |
| 1044 | "percentChangeColorMode": "standard", |
| 1045 | "reduceOptions": { |
| 1046 | "calcs": [ |
| 1047 | "lastNotNull" |
| 1048 | ], |
| 1049 | "fields": "", |
| 1050 | "values": false |
| 1051 | }, |
| 1052 | "showPercentChange": false, |
| 1053 | "textMode": "auto", |
| 1054 | "wideLayout": true |
| 1055 | }, |
| 1056 | "pluginVersion": "11.3.0", |
| 1057 | "targets": [ |
| 1058 | { |
| 1059 | "editorMode": "code", |
| 1060 | "expr": "histogram_quantile(0.99, sum by(le) (rate(vllm:inter_token_latency_seconds_bucket[$__range])))", |
| 1061 | "legendFormat": "__auto", |
| 1062 | "range": true, |
| 1063 | "refId": "A" |
| 1064 | } |
| 1065 | ], |
| 1066 | "title": "ITL (P99)", |
| 1067 | "type": "stat" |
| 1068 | }, |
| 1069 | { |
| 1070 | "datasource": { |
| 1071 | "type": "prometheus", |
| 1072 | "uid": "${DS_PROMETHEUS}" |
| 1073 | }, |
| 1074 | "description": "Average Iteration Latency (time per output token) over the selected time range.", |
| 1075 | "fieldConfig": { |
| 1076 | "defaults": { |
| 1077 | "color": { |
| 1078 | "mode": "thresholds" |
| 1079 | }, |
| 1080 | "decimals": 2, |
| 1081 | "mappings": [], |
| 1082 | "thresholds": { |
| 1083 | "mode": "absolute", |
| 1084 | "steps": [ |
| 1085 | { |
| 1086 | "color": "green", |
| 1087 | "value": null |
| 1088 | }, |
| 1089 | { |
| 1090 | "color": "red", |
| 1091 | "value": 80 |
| 1092 | } |
| 1093 | ] |
| 1094 | }, |
| 1095 | "unit": "s" |
| 1096 | }, |
| 1097 | "overrides": [] |
| 1098 | }, |
| 1099 | "gridPos": { |
| 1100 | "h": 4, |
| 1101 | "w": 6, |
| 1102 | "x": 12, |
| 1103 | "y": 23 |
| 1104 | }, |
| 1105 | "id": 16, |
| 1106 | "options": { |
| 1107 | "colorMode": "value", |
| 1108 | "graphMode": "area", |
| 1109 | "justifyMode": "auto", |
| 1110 | "orientation": "auto", |
| 1111 | "percentChangeColorMode": "standard", |
| 1112 | "reduceOptions": { |
| 1113 | "calcs": [ |
| 1114 | "lastNotNull" |
| 1115 | ], |
| 1116 | "fields": "", |
| 1117 | "values": false |
| 1118 | }, |
| 1119 | "showPercentChange": false, |
| 1120 | "textMode": "auto", |
| 1121 | "wideLayout": true |
| 1122 | }, |
| 1123 | "pluginVersion": "11.3.0", |
| 1124 | "targets": [ |
| 1125 | { |
| 1126 | "editorMode": "code", |
| 1127 | "expr": "(sum(increase(vllm:inter_token_latency_seconds_sum[$__range])) / sum(increase(vllm:inter_token_latency_seconds_count[$__range])))", |
| 1128 | "legendFormat": "__auto", |
| 1129 | "range": true, |
| 1130 | "refId": "A" |
| 1131 | } |
| 1132 | ], |
| 1133 | "title": "ITL (Avg)", |
| 1134 | "type": "stat" |
| 1135 | }, |
| 1136 | { |
| 1137 | "datasource": { |
| 1138 | "type": "prometheus", |
| 1139 | "uid": "${DS_PROMETHEUS}" |
| 1140 | }, |
| 1141 | "description": "50th percentile (median) of Iteration Latency over the selected time range.", |
| 1142 | "fieldConfig": { |
| 1143 | "defaults": { |
| 1144 | "color": { |
| 1145 | "mode": "thresholds" |
| 1146 | }, |
| 1147 | "decimals": 2, |
| 1148 | "mappings": [], |
| 1149 | "thresholds": { |
| 1150 | "mode": "absolute", |
| 1151 | "steps": [ |
| 1152 | { |
| 1153 | "color": "green", |
| 1154 | "value": null |
| 1155 | }, |
| 1156 | { |
| 1157 | "color": "red", |
| 1158 | "value": 80 |
| 1159 | } |
| 1160 | ] |
| 1161 | }, |
| 1162 | "unit": "s" |
| 1163 | }, |
| 1164 | "overrides": [] |
| 1165 | }, |
| 1166 | "gridPos": { |
| 1167 | "h": 4, |
| 1168 | "w": 6, |
| 1169 | "x": 18, |
| 1170 | "y": 23 |
| 1171 | }, |
| 1172 | "id": 17, |
| 1173 | "options": { |
| 1174 | "colorMode": "value", |
| 1175 | "graphMode": "area", |
| 1176 | "justifyMode": "auto", |
| 1177 | "orientation": "auto", |
| 1178 | "percentChangeColorMode": "standard", |
| 1179 | "reduceOptions": { |
| 1180 | "calcs": [ |
| 1181 | "lastNotNull" |
| 1182 | ], |
| 1183 | "fields": "", |
| 1184 | "values": false |
| 1185 | }, |
| 1186 | "showPercentChange": false, |
| 1187 | "textMode": "auto", |
| 1188 | "wideLayout": true |
| 1189 | }, |
| 1190 | "pluginVersion": "11.3.0", |
| 1191 | "targets": [ |
| 1192 | { |
| 1193 | "editorMode": "code", |
| 1194 | "expr": "histogram_quantile(0.50, sum by(le) (rate(vllm:inter_token_latency_seconds_bucket[$__range])))", |
| 1195 | "legendFormat": "__auto", |
| 1196 | "range": true, |
| 1197 | "refId": "A" |
| 1198 | } |
| 1199 | ], |
| 1200 | "title": "ITL (P50)", |
| 1201 | "type": "stat" |
| 1202 | }, |
| 1203 | { |
| 1204 | "collapsed": false, |
| 1205 | "gridPos": { |
| 1206 | "h": 1, |
| 1207 | "w": 24, |
| 1208 | "x": 0, |
| 1209 | "y": 27 |
| 1210 | }, |
| 1211 | "id": 6, |
| 1212 | "panels": [], |
| 1213 | "title": "TPS (Tokens Per Second)", |
| 1214 | "type": "row" |
| 1215 | }, |
| 1216 | { |
| 1217 | "datasource": { |
| 1218 | "type": "prometheus", |
| 1219 | "uid": "${DS_PROMETHEUS}" |
| 1220 | }, |
| 1221 | "description": "Rate of tokens processed per second, including prompt and generation phases.", |
| 1222 | "fieldConfig": { |
| 1223 | "defaults": { |
| 1224 | "color": { |
| 1225 | "mode": "palette-classic" |
| 1226 | }, |
| 1227 | "custom": { |
| 1228 | "axisBorderShow": false, |
| 1229 | "axisCenteredZero": false, |
| 1230 | "axisColorMode": "text", |
| 1231 | "axisLabel": "", |
| 1232 | "axisPlacement": "auto", |
| 1233 | "barAlignment": 0, |
| 1234 | "barWidthFactor": 0.6, |
| 1235 | "drawStyle": "line", |
| 1236 | "fillOpacity": 0, |
| 1237 | "gradientMode": "none", |
| 1238 | "hideFrom": { |
| 1239 | "legend": false, |
| 1240 | "tooltip": false, |
| 1241 | "viz": false |
| 1242 | }, |
| 1243 | "insertNulls": false, |
| 1244 | "lineInterpolation": "linear", |
| 1245 | "lineWidth": 1, |
| 1246 | "pointSize": 5, |
| 1247 | "scaleDistribution": { |
| 1248 | "type": "linear" |
| 1249 | }, |
| 1250 | "showPoints": "auto", |
| 1251 | "spanNulls": false, |
| 1252 | "stacking": { |
| 1253 | "group": "A", |
| 1254 | "mode": "none" |
| 1255 | }, |
| 1256 | "thresholdsStyle": { |
| 1257 | "mode": "off" |
| 1258 | } |
| 1259 | }, |
| 1260 | "mappings": [], |
| 1261 | "thresholds": { |
| 1262 | "mode": "absolute", |
| 1263 | "steps": [ |
| 1264 | { |
| 1265 | "color": "green", |
| 1266 | "value": null |
| 1267 | }, |
| 1268 | { |
| 1269 | "color": "red", |
| 1270 | "value": 80 |
| 1271 | } |
| 1272 | ] |
| 1273 | }, |
| 1274 | "unit": "tokens/sec (tps)" |
| 1275 | }, |
| 1276 | "overrides": [] |
| 1277 | }, |
| 1278 | "gridPos": { |
| 1279 | "h": 8, |
| 1280 | "w": 12, |
| 1281 | "x": 0, |
| 1282 | "y": 28 |
| 1283 | }, |
| 1284 | "id": 20, |
| 1285 | "options": { |
| 1286 | "legend": { |
| 1287 | "calcs": [], |
| 1288 | "displayMode": "list", |
| 1289 | "placement": "bottom", |
| 1290 | "showLegend": true |
| 1291 | }, |
| 1292 | "tooltip": { |
| 1293 | "mode": "single", |
| 1294 | "sort": "none" |
| 1295 | } |
| 1296 | }, |
| 1297 | "pluginVersion": "11.3.0", |
| 1298 | "targets": [ |
| 1299 | { |
| 1300 | "editorMode": "code", |
| 1301 | "expr": "rate(vllm:generation_tokens_total[$__interval])", |
| 1302 | "legendFormat": "Generation TPS", |
| 1303 | "range": true, |
| 1304 | "refId": "A" |
| 1305 | }, |
| 1306 | { |
| 1307 | "datasource": { |
| 1308 | "type": "prometheus", |
| 1309 | "uid": "${DS_PROMETHEUS}" |
| 1310 | }, |
| 1311 | "editorMode": "code", |
| 1312 | "expr": "rate(vllm:prompt_tokens_total[$__interval])", |
| 1313 | "hide": false, |
| 1314 | "instant": false, |
| 1315 | "legendFormat": "Prompt TPS", |
| 1316 | "range": true, |
| 1317 | "refId": "B" |
| 1318 | }, |
| 1319 | { |
| 1320 | "datasource": { |
| 1321 | "type": "prometheus", |
| 1322 | "uid": "${DS_PROMETHEUS}" |
| 1323 | }, |
| 1324 | "editorMode": "code", |
| 1325 | "expr": "rate(vllm:iteration_tokens_total_count[$__interval])", |
| 1326 | "hide": false, |
| 1327 | "instant": false, |
| 1328 | "legendFormat": "Overall Iteration TPS", |
| 1329 | "range": true, |
| 1330 | "refId": "C" |
| 1331 | } |
| 1332 | ], |
| 1333 | "title": "TPS (Tokens Per Second) Over Time", |
| 1334 | "type": "timeseries" |
| 1335 | } |
| 1336 | ], |
| 1337 | "preload": false, |
| 1338 | "schemaVersion": 40, |
| 1339 | "tags": [], |
| 1340 | "templating": { |
| 1341 | "list": [ |
| 1342 | { |
| 1343 | "name": "DS_PROMETHEUS", |
| 1344 | "type": "datasource", |
| 1345 | "label": "datasource", |
| 1346 | "query": "prometheus", |
| 1347 | "refresh": 1, |
| 1348 | "current": { |
| 1349 | "text": "Prometheus", |
| 1350 | "value": "prometheus" |
| 1351 | } |
| 1352 | }, |
| 1353 | { |
| 1354 | "current": { |
| 1355 | "text": "avg : Average\n0.50 : P50\n0.90 : P90\n0.99 : P99\n0.999 : Max (Approx)", |
| 1356 | "value": "avg : Average\n0.50 : P50\n0.90 : P90\n0.99 : P99\n0.999 : Max (Approx)" |
| 1357 | }, |
| 1358 | "label": "Aggregation", |
| 1359 | "name": "agg_method", |
| 1360 | "options": [ |
| 1361 | { |
| 1362 | "selected": true, |
| 1363 | "text": "avg : Average\n0.50 : P50\n0.90 : P90\n0.99 : P99\n0.999 : Max (Approx)", |
| 1364 | "value": "avg : Average\n0.50 : P50\n0.90 : P90\n0.99 : P99\n0.999 : Max (Approx)" |
| 1365 | } |
| 1366 | ], |
| 1367 | "query": "avg : Average\n0.50 : P50\n0.90 : P90\n0.99 : P99\n0.999 : Max (Approx)", |
| 1368 | "type": "custom" |
| 1369 | }, |
| 1370 | { |
| 1371 | "current": { |
| 1372 | "text": [ |
| 1373 | "granite-33-2b-instruct" |
| 1374 | ], |
| 1375 | "value": [ |
| 1376 | "granite-33-2b-instruct" |
| 1377 | ] |
| 1378 | }, |
| 1379 | "definition": "label_values(vllm:generation_tokens_total,model_name)", |
| 1380 | "includeAll": true, |
| 1381 | "label": "Deployment_ID", |
| 1382 | "multi": true, |
| 1383 | "name": "Deployment_id", |
| 1384 | "options": [], |
| 1385 | "query": { |
| 1386 | "qryType": 1, |
| 1387 | "query": "label_values(vllm:generation_tokens_total,model_name)", |
| 1388 | "refId": "PrometheusVariableQueryEditor-VariableQuery" |
| 1389 | }, |
| 1390 | "refresh": 1, |
| 1391 | "regex": "", |
| 1392 | "type": "query" |
| 1393 | } |
| 1394 | ] |
| 1395 | }, |
| 1396 | "time": { |
| 1397 | "from": "now-12h", |
| 1398 | "to": "now" |
| 1399 | }, |
| 1400 | "timezone": "browser", |
| 1401 | "uid": "performance-statistics", |
| 1402 | "title": "Performance Statistics", |
| 1403 | "version": 40, |
| 1404 | "weekStart": "" |
| 1405 | } |