grpc_surface.json
1 { 2 "grpc_server_module": "/home/mitko/dev/vllm/.venv/lib/python3.12/site-packages/vllm/entrypoints/grpc_server.py", 3 "messages": [ 4 { 5 "fields": [ 6 { 7 "label": "LABEL_OPTIONAL", 8 "name": "temperature", 9 "number": 1, 10 "type": "TYPE_FLOAT" 11 }, 12 { 13 "label": "LABEL_OPTIONAL", 14 "name": "top_p", 15 "number": 2, 16 "type": "TYPE_FLOAT" 17 }, 18 { 19 "label": "LABEL_OPTIONAL", 20 "name": "top_k", 21 "number": 3, 22 "type": "TYPE_UINT32" 23 }, 24 { 25 "label": "LABEL_OPTIONAL", 26 "name": "min_p", 27 "number": 4, 28 "type": "TYPE_FLOAT" 29 }, 30 { 31 "label": "LABEL_OPTIONAL", 32 "name": "frequency_penalty", 33 "number": 5, 34 "type": "TYPE_FLOAT" 35 }, 36 { 37 "label": "LABEL_OPTIONAL", 38 "name": "presence_penalty", 39 "number": 6, 40 "type": "TYPE_FLOAT" 41 }, 42 { 43 "label": "LABEL_OPTIONAL", 44 "name": "repetition_penalty", 45 "number": 7, 46 "type": "TYPE_FLOAT" 47 }, 48 { 49 "label": "LABEL_OPTIONAL", 50 "name": "max_tokens", 51 "number": 8, 52 "type": "TYPE_UINT32" 53 }, 54 { 55 "label": "LABEL_OPTIONAL", 56 "name": "min_tokens", 57 "number": 9, 58 "type": "TYPE_UINT32" 59 }, 60 { 61 "label": "LABEL_REPEATED", 62 "name": "stop", 63 "number": 10, 64 "type": "TYPE_STRING" 65 }, 66 { 67 "label": "LABEL_REPEATED", 68 "name": "stop_token_ids", 69 "number": 11, 70 "type": "TYPE_UINT32" 71 }, 72 { 73 "label": "LABEL_OPTIONAL", 74 "name": "skip_special_tokens", 75 "number": 12, 76 "type": "TYPE_BOOL" 77 }, 78 { 79 "label": "LABEL_OPTIONAL", 80 "name": "spaces_between_special_tokens", 81 "number": 13, 82 "type": "TYPE_BOOL" 83 }, 84 { 85 "label": "LABEL_OPTIONAL", 86 "name": "ignore_eos", 87 "number": 14, 88 "type": "TYPE_BOOL" 89 }, 90 { 91 "label": "LABEL_OPTIONAL", 92 "name": "n", 93 "number": 15, 94 "type": "TYPE_UINT32" 95 }, 96 { 97 "label": "LABEL_OPTIONAL", 98 "name": "logprobs", 99 "number": 22, 100 "type": "TYPE_INT32" 101 }, 102 { 103 "label": "LABEL_OPTIONAL", 104 "name": "prompt_logprobs", 105 "number": 23, 106 "type": "TYPE_INT32" 107 }, 108 { 109 "label": "LABEL_OPTIONAL", 110 "name": "seed", 111 "number": 24, 112 "type": "TYPE_INT32" 113 }, 114 { 115 "label": "LABEL_OPTIONAL", 116 "name": "include_stop_str_in_output", 117 "number": 25, 118 "type": "TYPE_BOOL" 119 }, 120 { 121 "label": "LABEL_REPEATED", 122 "name": "logit_bias", 123 "number": 26, 124 "type": "vllm.grpc.engine.SamplingParams.LogitBiasEntry" 125 }, 126 { 127 "label": "LABEL_OPTIONAL", 128 "name": "truncate_prompt_tokens", 129 "number": 27, 130 "type": "TYPE_INT32" 131 }, 132 { 133 "label": "LABEL_OPTIONAL", 134 "name": "json_schema", 135 "number": 16, 136 "type": "TYPE_STRING" 137 }, 138 { 139 "label": "LABEL_OPTIONAL", 140 "name": "regex", 141 "number": 17, 142 "type": "TYPE_STRING" 143 }, 144 { 145 "label": "LABEL_OPTIONAL", 146 "name": "grammar", 147 "number": 18, 148 "type": "TYPE_STRING" 149 }, 150 { 151 "label": "LABEL_OPTIONAL", 152 "name": "structural_tag", 153 "number": 19, 154 "type": "TYPE_STRING" 155 }, 156 { 157 "label": "LABEL_OPTIONAL", 158 "name": "json_object", 159 "number": 20, 160 "type": "TYPE_BOOL" 161 }, 162 { 163 "label": "LABEL_OPTIONAL", 164 "name": "choice", 165 "number": 21, 166 "type": "vllm.grpc.engine.ChoiceConstraint" 167 } 168 ], 169 "full_name": "vllm.grpc.engine.SamplingParams", 170 "name": "SamplingParams" 171 }, 172 { 173 "fields": [ 174 { 175 "label": "LABEL_REPEATED", 176 "name": "choices", 177 "number": 1, 178 "type": "TYPE_STRING" 179 } 180 ], 181 "full_name": "vllm.grpc.engine.ChoiceConstraint", 182 "name": "ChoiceConstraint" 183 }, 184 { 185 "fields": [ 186 { 187 "label": "LABEL_OPTIONAL", 188 "name": "original_text", 189 "number": 1, 190 "type": "TYPE_STRING" 191 }, 192 { 193 "label": "LABEL_REPEATED", 194 "name": "input_ids", 195 "number": 2, 196 "type": "TYPE_UINT32" 197 } 198 ], 199 "full_name": "vllm.grpc.engine.TokenizedInput", 200 "name": "TokenizedInput" 201 }, 202 { 203 "fields": [ 204 { 205 "label": "LABEL_OPTIONAL", 206 "name": "data", 207 "number": 1, 208 "type": "TYPE_BYTES" 209 }, 210 { 211 "label": "LABEL_REPEATED", 212 "name": "shape", 213 "number": 2, 214 "type": "TYPE_UINT32" 215 }, 216 { 217 "label": "LABEL_OPTIONAL", 218 "name": "dtype", 219 "number": 3, 220 "type": "TYPE_STRING" 221 } 222 ], 223 "full_name": "vllm.grpc.engine.TensorData", 224 "name": "TensorData" 225 }, 226 { 227 "fields": [ 228 { 229 "label": "LABEL_OPTIONAL", 230 "name": "offset", 231 "number": 1, 232 "type": "TYPE_UINT32" 233 }, 234 { 235 "label": "LABEL_OPTIONAL", 236 "name": "length", 237 "number": 2, 238 "type": "TYPE_UINT32" 239 } 240 ], 241 "full_name": "vllm.grpc.engine.PlaceholderRange", 242 "name": "PlaceholderRange" 243 }, 244 { 245 "fields": [ 246 { 247 "label": "LABEL_OPTIONAL", 248 "name": "pixel_values", 249 "number": 2, 250 "type": "vllm.grpc.engine.TensorData" 251 }, 252 { 253 "label": "LABEL_REPEATED", 254 "name": "model_specific_tensors", 255 "number": 3, 256 "type": "vllm.grpc.engine.MultimodalInputs.ModelSpecificTensorsEntry" 257 }, 258 { 259 "label": "LABEL_OPTIONAL", 260 "name": "im_token_id", 261 "number": 4, 262 "type": "TYPE_UINT32" 263 }, 264 { 265 "label": "LABEL_REPEATED", 266 "name": "mm_placeholders", 267 "number": 5, 268 "type": "vllm.grpc.engine.PlaceholderRange" 269 }, 270 { 271 "label": "LABEL_REPEATED", 272 "name": "mm_hashes", 273 "number": 6, 274 "type": "TYPE_STRING" 275 }, 276 { 277 "label": "LABEL_REPEATED", 278 "name": "batched_keys", 279 "number": 7, 280 "type": "TYPE_STRING" 281 }, 282 { 283 "label": "LABEL_REPEATED", 284 "name": "flat_keys", 285 "number": 8, 286 "type": "vllm.grpc.engine.MultimodalInputs.FlatKeysEntry" 287 }, 288 { 289 "label": "LABEL_REPEATED", 290 "name": "keep_on_cpu_keys", 291 "number": 9, 292 "type": "TYPE_STRING" 293 } 294 ], 295 "full_name": "vllm.grpc.engine.MultimodalInputs", 296 "name": "MultimodalInputs" 297 }, 298 { 299 "fields": [ 300 { 301 "label": "LABEL_OPTIONAL", 302 "name": "request_id", 303 "number": 1, 304 "type": "TYPE_STRING" 305 }, 306 { 307 "label": "LABEL_OPTIONAL", 308 "name": "tokenized", 309 "number": 2, 310 "type": "vllm.grpc.engine.TokenizedInput" 311 }, 312 { 313 "label": "LABEL_OPTIONAL", 314 "name": "text", 315 "number": 3, 316 "type": "TYPE_STRING" 317 }, 318 { 319 "label": "LABEL_OPTIONAL", 320 "name": "sampling_params", 321 "number": 4, 322 "type": "vllm.grpc.engine.SamplingParams" 323 }, 324 { 325 "label": "LABEL_OPTIONAL", 326 "name": "stream", 327 "number": 5, 328 "type": "TYPE_BOOL" 329 }, 330 { 331 "label": "LABEL_OPTIONAL", 332 "name": "kv_transfer_params", 333 "number": 6, 334 "type": "vllm.grpc.engine.KvTransferParams" 335 }, 336 { 337 "label": "LABEL_OPTIONAL", 338 "name": "mm_inputs", 339 "number": 7, 340 "type": "vllm.grpc.engine.MultimodalInputs" 341 } 342 ], 343 "full_name": "vllm.grpc.engine.GenerateRequest", 344 "name": "GenerateRequest" 345 }, 346 { 347 "fields": [ 348 { 349 "label": "LABEL_OPTIONAL", 350 "name": "remote_host", 351 "number": 1, 352 "type": "TYPE_STRING" 353 }, 354 { 355 "label": "LABEL_OPTIONAL", 356 "name": "remote_port", 357 "number": 2, 358 "type": "TYPE_UINT32" 359 } 360 ], 361 "full_name": "vllm.grpc.engine.KvTransferParams", 362 "name": "KvTransferParams" 363 }, 364 { 365 "fields": [ 366 { 367 "label": "LABEL_REPEATED", 368 "name": "token_logprobs", 369 "number": 1, 370 "type": "TYPE_FLOAT" 371 }, 372 { 373 "label": "LABEL_REPEATED", 374 "name": "token_ids", 375 "number": 2, 376 "type": "TYPE_UINT32" 377 }, 378 { 379 "label": "LABEL_REPEATED", 380 "name": "top_logprobs", 381 "number": 3, 382 "type": "vllm.grpc.engine.TopLogProbs" 383 } 384 ], 385 "full_name": "vllm.grpc.engine.OutputLogProbs", 386 "name": "OutputLogProbs" 387 }, 388 { 389 "fields": [ 390 { 391 "label": "LABEL_REPEATED", 392 "name": "token_logprobs", 393 "number": 1, 394 "type": "vllm.grpc.engine.InputTokenLogProb" 395 }, 396 { 397 "label": "LABEL_REPEATED", 398 "name": "token_ids", 399 "number": 2, 400 "type": "TYPE_UINT32" 401 }, 402 { 403 "label": "LABEL_REPEATED", 404 "name": "top_logprobs", 405 "number": 3, 406 "type": "vllm.grpc.engine.TopLogProbs" 407 } 408 ], 409 "full_name": "vllm.grpc.engine.InputLogProbs", 410 "name": "InputLogProbs" 411 }, 412 { 413 "fields": [ 414 { 415 "label": "LABEL_OPTIONAL", 416 "name": "value", 417 "number": 1, 418 "type": "TYPE_FLOAT" 419 } 420 ], 421 "full_name": "vllm.grpc.engine.InputTokenLogProb", 422 "name": "InputTokenLogProb" 423 }, 424 { 425 "fields": [ 426 { 427 "label": "LABEL_REPEATED", 428 "name": "values", 429 "number": 1, 430 "type": "TYPE_FLOAT" 431 }, 432 { 433 "label": "LABEL_REPEATED", 434 "name": "token_ids", 435 "number": 2, 436 "type": "TYPE_UINT32" 437 } 438 ], 439 "full_name": "vllm.grpc.engine.TopLogProbs", 440 "name": "TopLogProbs" 441 }, 442 { 443 "fields": [ 444 { 445 "label": "LABEL_OPTIONAL", 446 "name": "chunk", 447 "number": 1, 448 "type": "vllm.grpc.engine.GenerateStreamChunk" 449 }, 450 { 451 "label": "LABEL_OPTIONAL", 452 "name": "complete", 453 "number": 2, 454 "type": "vllm.grpc.engine.GenerateComplete" 455 } 456 ], 457 "full_name": "vllm.grpc.engine.GenerateResponse", 458 "name": "GenerateResponse" 459 }, 460 { 461 "fields": [ 462 { 463 "label": "LABEL_REPEATED", 464 "name": "token_ids", 465 "number": 1, 466 "type": "TYPE_UINT32" 467 }, 468 { 469 "label": "LABEL_OPTIONAL", 470 "name": "prompt_tokens", 471 "number": 2, 472 "type": "TYPE_UINT32" 473 }, 474 { 475 "label": "LABEL_OPTIONAL", 476 "name": "completion_tokens", 477 "number": 3, 478 "type": "TYPE_UINT32" 479 }, 480 { 481 "label": "LABEL_OPTIONAL", 482 "name": "cached_tokens", 483 "number": 4, 484 "type": "TYPE_UINT32" 485 }, 486 { 487 "label": "LABEL_OPTIONAL", 488 "name": "output_logprobs", 489 "number": 5, 490 "type": "vllm.grpc.engine.OutputLogProbs" 491 }, 492 { 493 "label": "LABEL_OPTIONAL", 494 "name": "input_logprobs", 495 "number": 6, 496 "type": "vllm.grpc.engine.InputLogProbs" 497 }, 498 { 499 "label": "LABEL_OPTIONAL", 500 "name": "index", 501 "number": 7, 502 "type": "TYPE_UINT32" 503 } 504 ], 505 "full_name": "vllm.grpc.engine.GenerateStreamChunk", 506 "name": "GenerateStreamChunk" 507 }, 508 { 509 "fields": [ 510 { 511 "label": "LABEL_REPEATED", 512 "name": "output_ids", 513 "number": 1, 514 "type": "TYPE_UINT32" 515 }, 516 { 517 "label": "LABEL_OPTIONAL", 518 "name": "finish_reason", 519 "number": 2, 520 "type": "TYPE_STRING" 521 }, 522 { 523 "label": "LABEL_OPTIONAL", 524 "name": "prompt_tokens", 525 "number": 3, 526 "type": "TYPE_UINT32" 527 }, 528 { 529 "label": "LABEL_OPTIONAL", 530 "name": "completion_tokens", 531 "number": 4, 532 "type": "TYPE_UINT32" 533 }, 534 { 535 "label": "LABEL_OPTIONAL", 536 "name": "cached_tokens", 537 "number": 5, 538 "type": "TYPE_UINT32" 539 }, 540 { 541 "label": "LABEL_OPTIONAL", 542 "name": "output_logprobs", 543 "number": 6, 544 "type": "vllm.grpc.engine.OutputLogProbs" 545 }, 546 { 547 "label": "LABEL_OPTIONAL", 548 "name": "input_logprobs", 549 "number": 7, 550 "type": "vllm.grpc.engine.InputLogProbs" 551 }, 552 { 553 "label": "LABEL_OPTIONAL", 554 "name": "index", 555 "number": 8, 556 "type": "TYPE_UINT32" 557 }, 558 { 559 "label": "LABEL_OPTIONAL", 560 "name": "kv_transfer_params", 561 "number": 9, 562 "type": "vllm.grpc.engine.KvTransferParams" 563 }, 564 { 565 "label": "LABEL_OPTIONAL", 566 "name": "matched_token_id", 567 "number": 10, 568 "type": "TYPE_UINT32" 569 }, 570 { 571 "label": "LABEL_OPTIONAL", 572 "name": "matched_stop_str", 573 "number": 11, 574 "type": "TYPE_STRING" 575 } 576 ], 577 "full_name": "vllm.grpc.engine.GenerateComplete", 578 "name": "GenerateComplete" 579 }, 580 { 581 "fields": [ 582 { 583 "label": "LABEL_OPTIONAL", 584 "name": "request_id", 585 "number": 1, 586 "type": "TYPE_STRING" 587 }, 588 { 589 "label": "LABEL_OPTIONAL", 590 "name": "tokenized", 591 "number": 2, 592 "type": "vllm.grpc.engine.TokenizedInput" 593 } 594 ], 595 "full_name": "vllm.grpc.engine.EmbedRequest", 596 "name": "EmbedRequest" 597 }, 598 { 599 "fields": [ 600 { 601 "label": "LABEL_REPEATED", 602 "name": "embedding", 603 "number": 1, 604 "type": "TYPE_FLOAT" 605 }, 606 { 607 "label": "LABEL_OPTIONAL", 608 "name": "prompt_tokens", 609 "number": 2, 610 "type": "TYPE_UINT32" 611 }, 612 { 613 "label": "LABEL_OPTIONAL", 614 "name": "embedding_dim", 615 "number": 3, 616 "type": "TYPE_UINT32" 617 } 618 ], 619 "full_name": "vllm.grpc.engine.EmbedResponse", 620 "name": "EmbedResponse" 621 }, 622 { 623 "fields": [], 624 "full_name": "vllm.grpc.engine.HealthCheckRequest", 625 "name": "HealthCheckRequest" 626 }, 627 { 628 "fields": [ 629 { 630 "label": "LABEL_OPTIONAL", 631 "name": "healthy", 632 "number": 1, 633 "type": "TYPE_BOOL" 634 }, 635 { 636 "label": "LABEL_OPTIONAL", 637 "name": "message", 638 "number": 2, 639 "type": "TYPE_STRING" 640 } 641 ], 642 "full_name": "vllm.grpc.engine.HealthCheckResponse", 643 "name": "HealthCheckResponse" 644 }, 645 { 646 "fields": [ 647 { 648 "label": "LABEL_REPEATED", 649 "name": "request_ids", 650 "number": 1, 651 "type": "TYPE_STRING" 652 } 653 ], 654 "full_name": "vllm.grpc.engine.AbortRequest", 655 "name": "AbortRequest" 656 }, 657 { 658 "fields": [], 659 "full_name": "vllm.grpc.engine.AbortResponse", 660 "name": "AbortResponse" 661 }, 662 { 663 "fields": [], 664 "full_name": "vllm.grpc.engine.GetModelInfoRequest", 665 "name": "GetModelInfoRequest" 666 }, 667 { 668 "fields": [ 669 { 670 "label": "LABEL_OPTIONAL", 671 "name": "model_path", 672 "number": 1, 673 "type": "TYPE_STRING" 674 }, 675 { 676 "label": "LABEL_OPTIONAL", 677 "name": "is_generation", 678 "number": 2, 679 "type": "TYPE_BOOL" 680 }, 681 { 682 "label": "LABEL_OPTIONAL", 683 "name": "max_context_length", 684 "number": 3, 685 "type": "TYPE_UINT32" 686 }, 687 { 688 "label": "LABEL_OPTIONAL", 689 "name": "vocab_size", 690 "number": 4, 691 "type": "TYPE_UINT32" 692 }, 693 { 694 "label": "LABEL_OPTIONAL", 695 "name": "supports_vision", 696 "number": 5, 697 "type": "TYPE_BOOL" 698 }, 699 { 700 "label": "LABEL_OPTIONAL", 701 "name": "served_model_name", 702 "number": 6, 703 "type": "TYPE_STRING" 704 } 705 ], 706 "full_name": "vllm.grpc.engine.GetModelInfoResponse", 707 "name": "GetModelInfoResponse" 708 }, 709 { 710 "fields": [], 711 "full_name": "vllm.grpc.engine.GetServerInfoRequest", 712 "name": "GetServerInfoRequest" 713 }, 714 { 715 "fields": [ 716 { 717 "label": "LABEL_OPTIONAL", 718 "name": "active_requests", 719 "number": 1, 720 "type": "TYPE_UINT32" 721 }, 722 { 723 "label": "LABEL_OPTIONAL", 724 "name": "is_paused", 725 "number": 2, 726 "type": "TYPE_BOOL" 727 }, 728 { 729 "label": "LABEL_OPTIONAL", 730 "name": "last_receive_timestamp", 731 "number": 3, 732 "type": "TYPE_DOUBLE" 733 }, 734 { 735 "label": "LABEL_OPTIONAL", 736 "name": "uptime_seconds", 737 "number": 4, 738 "type": "TYPE_DOUBLE" 739 }, 740 { 741 "label": "LABEL_OPTIONAL", 742 "name": "server_type", 743 "number": 5, 744 "type": "TYPE_STRING" 745 }, 746 { 747 "label": "LABEL_OPTIONAL", 748 "name": "kv_connector", 749 "number": 6, 750 "type": "TYPE_STRING" 751 }, 752 { 753 "label": "LABEL_OPTIONAL", 754 "name": "kv_role", 755 "number": 7, 756 "type": "TYPE_STRING" 757 } 758 ], 759 "full_name": "vllm.grpc.engine.GetServerInfoResponse", 760 "name": "GetServerInfoResponse" 761 } 762 ], 763 "modules": { 764 "smg_grpc_proto.generated.common_pb2": "/home/mitko/dev/vllm/.venv/lib/python3.12/site-packages/smg_grpc_proto/generated/common_pb2.py", 765 "smg_grpc_proto.generated.vllm_engine_pb2": "/home/mitko/dev/vllm/.venv/lib/python3.12/site-packages/smg_grpc_proto/generated/vllm_engine_pb2.py", 766 "smg_grpc_proto.generated.vllm_engine_pb2_grpc": "/home/mitko/dev/vllm/.venv/lib/python3.12/site-packages/smg_grpc_proto/generated/vllm_engine_pb2_grpc.py", 767 "vllm.entrypoints.grpc_server": "/home/mitko/dev/vllm/.venv/lib/python3.12/site-packages/vllm/entrypoints/grpc_server.py" 768 }, 769 "proto_files": [ 770 { 771 "name": "vllm_engine.proto", 772 "package": "vllm.grpc.engine" 773 }, 774 { 775 "name": "common.proto", 776 "package": "smg.grpc.common" 777 } 778 ], 779 "protobuf_packages": [ 780 "smg.grpc.common", 781 "vllm.grpc.engine" 782 ], 783 "python_executable": "/home/mitko/dev/vllm/.venv/bin/python", 784 "runtime_probe": { 785 "endpoint": "localhost:8000", 786 "health": { 787 "healthy": true, 788 "message": "Health" 789 }, 790 "model_info": { 791 "is_generation": true, 792 "max_context_length": 262144, 793 "model_path": "mitko", 794 "served_model_name": "mitko", 795 "supports_vision": true 796 }, 797 "server_info": { 798 "active_requests": 0, 799 "is_paused": false, 800 "server_type": "vllm-grpc", 801 "uptime_seconds": 736.4940102100372 802 }, 803 "tokenizer": { 804 "code": "UNIMPLEMENTED", 805 "details": "Unexpected <class 'NotImplementedError'>: Method not implemented!", 806 "implemented": false 807 } 808 }, 809 "services": [ 810 { 811 "full_name": "vllm.grpc.engine.VllmEngine", 812 "methods": [ 813 { 814 "client_streaming": false, 815 "full_name": "/vllm.grpc.engine.VllmEngine/Generate", 816 "name": "Generate", 817 "request_type": "vllm.grpc.engine.GenerateRequest", 818 "response_type": "vllm.grpc.engine.GenerateResponse", 819 "server_streaming": true 820 }, 821 { 822 "client_streaming": false, 823 "full_name": "/vllm.grpc.engine.VllmEngine/Embed", 824 "name": "Embed", 825 "request_type": "vllm.grpc.engine.EmbedRequest", 826 "response_type": "vllm.grpc.engine.EmbedResponse", 827 "server_streaming": false 828 }, 829 { 830 "client_streaming": false, 831 "full_name": "/vllm.grpc.engine.VllmEngine/HealthCheck", 832 "name": "HealthCheck", 833 "request_type": "vllm.grpc.engine.HealthCheckRequest", 834 "response_type": "vllm.grpc.engine.HealthCheckResponse", 835 "server_streaming": false 836 }, 837 { 838 "client_streaming": false, 839 "full_name": "/vllm.grpc.engine.VllmEngine/Abort", 840 "name": "Abort", 841 "request_type": "vllm.grpc.engine.AbortRequest", 842 "response_type": "vllm.grpc.engine.AbortResponse", 843 "server_streaming": false 844 }, 845 { 846 "client_streaming": false, 847 "full_name": "/vllm.grpc.engine.VllmEngine/GetModelInfo", 848 "name": "GetModelInfo", 849 "request_type": "vllm.grpc.engine.GetModelInfoRequest", 850 "response_type": "vllm.grpc.engine.GetModelInfoResponse", 851 "server_streaming": false 852 }, 853 { 854 "client_streaming": false, 855 "full_name": "/vllm.grpc.engine.VllmEngine/GetServerInfo", 856 "name": "GetServerInfo", 857 "request_type": "vllm.grpc.engine.GetServerInfoRequest", 858 "response_type": "vllm.grpc.engine.GetServerInfoResponse", 859 "server_streaming": false 860 }, 861 { 862 "client_streaming": false, 863 "full_name": "/vllm.grpc.engine.VllmEngine/GetTokenizer", 864 "name": "GetTokenizer", 865 "request_type": "smg.grpc.common.GetTokenizerRequest", 866 "response_type": "smg.grpc.common.GetTokenizerChunk", 867 "server_streaming": true 868 }, 869 { 870 "client_streaming": false, 871 "full_name": "/vllm.grpc.engine.VllmEngine/SubscribeKvEvents", 872 "name": "SubscribeKvEvents", 873 "request_type": "smg.grpc.common.SubscribeKvEventsRequest", 874 "response_type": "smg.grpc.common.KvEventBatch", 875 "server_streaming": true 876 } 877 ], 878 "name": "VllmEngine" 879 } 880 ], 881 "streaming_methods": [ 882 { 883 "client_streaming": false, 884 "full_name": "/vllm.grpc.engine.VllmEngine/Generate", 885 "name": "Generate", 886 "request_type": "vllm.grpc.engine.GenerateRequest", 887 "response_type": "vllm.grpc.engine.GenerateResponse", 888 "server_streaming": true 889 }, 890 { 891 "client_streaming": false, 892 "full_name": "/vllm.grpc.engine.VllmEngine/GetTokenizer", 893 "name": "GetTokenizer", 894 "request_type": "smg.grpc.common.GetTokenizerRequest", 895 "response_type": "smg.grpc.common.GetTokenizerChunk", 896 "server_streaming": true 897 }, 898 { 899 "client_streaming": false, 900 "full_name": "/vllm.grpc.engine.VllmEngine/SubscribeKvEvents", 901 "name": "SubscribeKvEvents", 902 "request_type": "smg.grpc.common.SubscribeKvEventsRequest", 903 "response_type": "smg.grpc.common.KvEventBatch", 904 "server_streaming": true 905 } 906 ] 907 }