vllm.v1.metrics.loggers ¶
AggregateStatLoggerFactory module-attribute
¶
AggregateStatLoggerFactory = type["AggregateStatLoggerBase"]
PerEngineStatLoggerFactory module-attribute
¶
PerEngineStatLoggerFactory = Callable[
[VllmConfig, int], "StatLoggerBase"
]
StatLoggerFactory module-attribute
¶
StatLoggerFactory = (
AggregateStatLoggerFactory | PerEngineStatLoggerFactory
)
AggregateStatLoggerBase ¶
Bases: StatLoggerBase
Abstract base class for loggers that aggregate across multiple DP engines.
Source code in vllm/v1/metrics/loggers.py
AggregatedLoggingStatLogger ¶
Bases: LoggingStatLogger
, AggregateStatLoggerBase
Source code in vllm/v1/metrics/loggers.py
last_scheduler_stats_dict instance-attribute
¶
last_scheduler_stats_dict: dict[int, SchedulerStats] = {
idx: (SchedulerStats()) for idx in (engine_indexes)
}
__init__ ¶
__init__(
vllm_config: VllmConfig, engine_indexes: list[int]
)
Source code in vllm/v1/metrics/loggers.py
aggregate_scheduler_stats ¶
Source code in vllm/v1/metrics/loggers.py
log ¶
log_engine_initialized ¶
Source code in vllm/v1/metrics/loggers.py
record ¶
record(
scheduler_stats: SchedulerStats | None,
iteration_stats: IterationStats | None,
mm_cache_stats: MultiModalCacheStats | None = None,
engine_idx: int = 0,
)
Source code in vllm/v1/metrics/loggers.py
LoggingStatLogger ¶
Bases: StatLoggerBase
Source code in vllm/v1/metrics/loggers.py
67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 |
|
kv_connector_logging instance-attribute
¶
kv_connector_logging = KVConnectorLogging(kv_tranfer_config)
__init__ ¶
__init__(vllm_config: VllmConfig, engine_index: int = 0)
Source code in vllm/v1/metrics/loggers.py
_get_throughput ¶
_reset ¶
_track_iteration_stats ¶
_track_iteration_stats(iteration_stats: IterationStats)
_update_stats ¶
Source code in vllm/v1/metrics/loggers.py
aggregate_scheduler_stats ¶
log ¶
Source code in vllm/v1/metrics/loggers.py
log_engine_initialized ¶
Source code in vllm/v1/metrics/loggers.py
record ¶
record(
scheduler_stats: SchedulerStats | None,
iteration_stats: IterationStats | None,
mm_cache_stats: MultiModalCacheStats | None = None,
engine_idx: int = 0,
)
Log Stats to standard output.
Source code in vllm/v1/metrics/loggers.py
PerEngineStatLoggerAdapter ¶
Bases: AggregateStatLoggerBase
Source code in vllm/v1/metrics/loggers.py
__init__ ¶
__init__(
vllm_config: VllmConfig,
engine_indexes: list[int],
per_engine_stat_logger_factory: PerEngineStatLoggerFactory,
) -> None
Source code in vllm/v1/metrics/loggers.py
log ¶
log_engine_initialized ¶
record ¶
record(
scheduler_stats: SchedulerStats | None,
iteration_stats: IterationStats | None,
mm_cache_stats: MultiModalCacheStats | None = None,
engine_idx: int = 0,
)
Source code in vllm/v1/metrics/loggers.py
PrometheusStatLogger ¶
Bases: AggregateStatLoggerBase
Source code in vllm/v1/metrics/loggers.py
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 |
|
counter_generation_tokens instance-attribute
¶
counter_generation_tokens = make_per_engine(
counter_generation_tokens, engine_indexes, model_name
)
counter_gpu_prefix_cache_hits instance-attribute
¶
counter_gpu_prefix_cache_hits = make_per_engine(
counter_gpu_prefix_cache_hits,
engine_indexes,
model_name,
)
counter_gpu_prefix_cache_queries instance-attribute
¶
counter_gpu_prefix_cache_queries = make_per_engine(
counter_gpu_prefix_cache_queries,
engine_indexes,
model_name,
)
counter_mm_cache_hits instance-attribute
¶
counter_mm_cache_hits = make_per_engine(
counter_mm_cache_hits, engine_indexes, model_name
)
counter_mm_cache_queries instance-attribute
¶
counter_mm_cache_queries = make_per_engine(
counter_mm_cache_queries, engine_indexes, model_name
)
counter_num_preempted_reqs instance-attribute
¶
counter_num_preempted_reqs = make_per_engine(
counter_num_preempted_reqs, engine_indexes, model_name
)
counter_prefix_cache_hits instance-attribute
¶
counter_prefix_cache_hits = make_per_engine(
counter_prefix_cache_hits, engine_indexes, model_name
)
counter_prefix_cache_queries instance-attribute
¶
counter_prefix_cache_queries = make_per_engine(
counter_prefix_cache_queries, engine_indexes, model_name
)
counter_prompt_tokens instance-attribute
¶
counter_prompt_tokens = make_per_engine(
counter_prompt_tokens, engine_indexes, model_name
)
counter_request_success instance-attribute
¶
counter_request_success: dict[
FinishReason, dict[int, Counter]
] = {}
gauge_gpu_cache_usage instance-attribute
¶
gauge_gpu_cache_usage = make_per_engine(
gauge_gpu_cache_usage, engine_indexes, model_name
)
gauge_kv_cache_usage instance-attribute
¶
gauge_kv_cache_usage = make_per_engine(
gauge_kv_cache_usage, engine_indexes, model_name
)
gauge_scheduler_running instance-attribute
¶
gauge_scheduler_running = make_per_engine(
gauge_scheduler_running, engine_indexes, model_name
)
gauge_scheduler_waiting instance-attribute
¶
gauge_scheduler_waiting = make_per_engine(
gauge_scheduler_waiting, engine_indexes, model_name
)
histogram_decode_time_request instance-attribute
¶
histogram_decode_time_request = make_per_engine(
histogram_decode_time_request,
engine_indexes,
model_name,
)
histogram_e2e_time_request instance-attribute
¶
histogram_e2e_time_request = make_per_engine(
histogram_e2e_time_request, engine_indexes, model_name
)
histogram_inference_time_request instance-attribute
¶
histogram_inference_time_request = make_per_engine(
histogram_inference_time_request,
engine_indexes,
model_name,
)
histogram_inter_token_latency instance-attribute
¶
histogram_inter_token_latency = make_per_engine(
histogram_inter_token_latency,
engine_indexes,
model_name,
)
histogram_iteration_tokens instance-attribute
¶
histogram_iteration_tokens = make_per_engine(
histogram_iteration_tokens, engine_indexes, model_name
)
histogram_max_num_generation_tokens_request instance-attribute
¶
histogram_max_num_generation_tokens_request = (
make_per_engine(
histogram_max_num_generation_tokens_request,
engine_indexes,
model_name,
)
)
histogram_max_tokens_request instance-attribute
¶
histogram_max_tokens_request = make_per_engine(
histogram_max_tokens_request, engine_indexes, model_name
)
histogram_n_request instance-attribute
¶
histogram_n_request = make_per_engine(
histogram_n_request, engine_indexes, model_name
)
histogram_num_generation_tokens_request instance-attribute
¶
histogram_num_generation_tokens_request = make_per_engine(
histogram_num_generation_tokens_request,
engine_indexes,
model_name,
)
histogram_num_prompt_tokens_request instance-attribute
¶
histogram_num_prompt_tokens_request = make_per_engine(
histogram_num_prompt_tokens_request,
engine_indexes,
model_name,
)
histogram_prefill_time_request instance-attribute
¶
histogram_prefill_time_request = make_per_engine(
histogram_prefill_time_request,
engine_indexes,
model_name,
)
histogram_queue_time_request instance-attribute
¶
histogram_queue_time_request = make_per_engine(
histogram_queue_time_request, engine_indexes, model_name
)
histogram_request_time_per_output_token instance-attribute
¶
histogram_request_time_per_output_token = make_per_engine(
histogram_request_time_per_output_token,
engine_indexes,
model_name,
)
histogram_time_per_output_token instance-attribute
¶
histogram_time_per_output_token = make_per_engine(
histogram_time_per_output_token,
engine_indexes,
model_name,
)
histogram_time_to_first_token instance-attribute
¶
histogram_time_to_first_token = make_per_engine(
histogram_time_to_first_token,
engine_indexes,
model_name,
)
labelname_running_lora_adapters instance-attribute
¶
labelname_waiting_lora_adapters instance-attribute
¶
spec_decoding_prom instance-attribute
¶
__init__ ¶
__init__(
vllm_config: VllmConfig,
engine_indexes: list[int] | None = None,
)
Source code in vllm/v1/metrics/loggers.py
312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 |
|
log_engine_initialized ¶
log_metrics_info ¶
log_metrics_info(
type: str, config_obj: SupportsMetricsInfo
)
Source code in vllm/v1/metrics/loggers.py
record ¶
record(
scheduler_stats: SchedulerStats | None,
iteration_stats: IterationStats | None,
mm_cache_stats: MultiModalCacheStats | None = None,
engine_idx: int = 0,
)
Log to prometheus.
Source code in vllm/v1/metrics/loggers.py
831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 |
|
StatLoggerBase ¶
Bases: ABC
Interface for logging metrics.
API users may define custom loggers that implement this interface. However, note that the SchedulerStats
and IterationStats
classes are not considered stable interfaces and may change in future versions.
Source code in vllm/v1/metrics/loggers.py
__init__ abstractmethod
¶
__init__(vllm_config: VllmConfig, engine_index: int = 0)
log_engine_initialized abstractmethod
¶
record abstractmethod
¶
record(
scheduler_stats: SchedulerStats | None,
iteration_stats: IterationStats | None,
mm_cache_stats: MultiModalCacheStats | None = None,
engine_idx: int = 0,
)
StatLoggerManager ¶
StatLoggerManager
Logging happens at the level of the EngineCore (per scheduler). * DP: >1 EngineCore per AsyncLLM - loggers for each EngineCore. * With Local Logger, just make N copies for N EngineCores. * With Prometheus, we need a single logger with N "labels"
This class abstracts away this implementation detail from the AsyncLLM, allowing the AsyncLLM to just call .record() and .log() to a simple interface.
Source code in vllm/v1/metrics/loggers.py
990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 |
|
__init__ ¶
__init__(
vllm_config: VllmConfig,
engine_idxs: list[int] | None = None,
custom_stat_loggers: list[StatLoggerFactory]
| None = None,
enable_default_loggers: bool = True,
aggregate_engine_logging: bool = False,
client_count: int = 1,
)
Source code in vllm/v1/metrics/loggers.py
log ¶
log_engine_initialized ¶
record ¶
record(
scheduler_stats: SchedulerStats | None,
iteration_stats: IterationStats | None,
mm_cache_stats: MultiModalCacheStats | None = None,
engine_idx: int | None = None,
)
Source code in vllm/v1/metrics/loggers.py
build_1_2_5_buckets ¶
build_buckets ¶
Builds a list of buckets with increasing powers of 10 multiplied by mantissa values until the value exceeds the specified maximum.
Source code in vllm/v1/metrics/loggers.py
make_per_engine ¶
make_per_engine(
metric: PromMetric,
engine_idxs: list[int],
model_name: str,
) -> dict[int, PromMetric]