-
Notifications
You must be signed in to change notification settings - Fork 74
/
Copy pathgrpc_service.proto
1810 lines (1631 loc) · 48.4 KB
/
grpc_service.proto
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
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
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
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
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// Copyright 2020-2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions
// are met:
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above copyright
// notice, this list of conditions and the following disclaimer in the
// documentation and/or other materials provided with the distribution.
// * Neither the name of NVIDIA CORPORATION nor the names of its
// contributors may be used to endorse or promote products derived
// from this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
// PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
// OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
syntax = "proto3";
package inference;
//@@.. cpp:namespace:: inference
import "model_config.proto";
//@@
//@@.. cpp:var:: service InferenceService
//@@
//@@ Inference Server GRPC endpoints.
//@@
service GRPCInferenceService
{
//@@ .. cpp:var:: rpc ServerLive(ServerLiveRequest) returns
//@@ (ServerLiveResponse)
//@@
//@@ Check liveness of the inference server.
//@@
rpc ServerLive(ServerLiveRequest) returns (ServerLiveResponse) {}
//@@ .. cpp:var:: rpc ServerReady(ServerReadyRequest) returns
//@@ (ServerReadyResponse)
//@@
//@@ Check readiness of the inference server.
//@@
rpc ServerReady(ServerReadyRequest) returns (ServerReadyResponse) {}
//@@ .. cpp:var:: rpc ModelReady(ModelReadyRequest) returns
//@@ (ModelReadyResponse)
//@@
//@@ Check readiness of a model in the inference server.
//@@
rpc ModelReady(ModelReadyRequest) returns (ModelReadyResponse) {}
//@@ .. cpp:var:: rpc ServerMetadata(ServerMetadataRequest) returns
//@@ (ServerMetadataResponse)
//@@
//@@ Get server metadata.
//@@
rpc ServerMetadata(ServerMetadataRequest) returns (ServerMetadataResponse) {}
//@@ .. cpp:var:: rpc ModelMetadata(ModelMetadataRequest) returns
//@@ (ModelMetadataResponse)
//@@
//@@ Get model metadata.
//@@
rpc ModelMetadata(ModelMetadataRequest) returns (ModelMetadataResponse) {}
//@@ .. cpp:var:: rpc ModelInfer(ModelInferRequest) returns
//@@ (ModelInferResponse)
//@@
//@@ Perform inference using a specific model.
//@@
rpc ModelInfer(ModelInferRequest) returns (ModelInferResponse) {}
//@@ .. cpp:var:: rpc ModelStreamInfer(stream ModelInferRequest) returns
//@@ (stream ModelStreamInferResponse)
//@@
//@@ Perform streaming inference.
//@@
rpc ModelStreamInfer(stream ModelInferRequest)
returns (stream ModelStreamInferResponse)
{
}
//@@ .. cpp:var:: rpc ModelConfig(ModelConfigRequest) returns
//@@ (ModelConfigResponse)
//@@
//@@ Get model configuration.
//@@
rpc ModelConfig(ModelConfigRequest) returns (ModelConfigResponse) {}
//@@ .. cpp:var:: rpc ModelStatistics(
//@@ ModelStatisticsRequest)
//@@ returns (ModelStatisticsResponse)
//@@
//@@ Get the cumulative inference statistics for a model.
//@@
rpc ModelStatistics(ModelStatisticsRequest) returns (ModelStatisticsResponse)
{
}
//@@ .. cpp:var:: rpc RepositoryIndex(RepositoryIndexRequest) returns
//@@ (RepositoryIndexResponse)
//@@
//@@ Get the index of model repository contents.
//@@
rpc RepositoryIndex(RepositoryIndexRequest) returns (RepositoryIndexResponse)
{
}
//@@ .. cpp:var:: rpc RepositoryModelLoad(RepositoryModelLoadRequest) returns
//@@ (RepositoryModelLoadResponse)
//@@
//@@ Load or reload a model from a repository.
//@@
rpc RepositoryModelLoad(RepositoryModelLoadRequest)
returns (RepositoryModelLoadResponse)
{
}
//@@ .. cpp:var:: rpc RepositoryModelUnload(RepositoryModelUnloadRequest)
//@@ returns (RepositoryModelUnloadResponse)
//@@
//@@ Unload a model.
//@@
rpc RepositoryModelUnload(RepositoryModelUnloadRequest)
returns (RepositoryModelUnloadResponse)
{
}
//@@ .. cpp:var:: rpc SystemSharedMemoryStatus(
//@@ SystemSharedMemoryStatusRequest)
//@@ returns (SystemSharedMemoryStatusRespose)
//@@
//@@ Get the status of all registered system-shared-memory regions.
//@@
rpc SystemSharedMemoryStatus(SystemSharedMemoryStatusRequest)
returns (SystemSharedMemoryStatusResponse)
{
}
//@@ .. cpp:var:: rpc SystemSharedMemoryRegister(
//@@ SystemSharedMemoryRegisterRequest)
//@@ returns (SystemSharedMemoryRegisterResponse)
//@@
//@@ Register a system-shared-memory region.
//@@
rpc SystemSharedMemoryRegister(SystemSharedMemoryRegisterRequest)
returns (SystemSharedMemoryRegisterResponse)
{
}
//@@ .. cpp:var:: rpc SystemSharedMemoryUnregister(
//@@ SystemSharedMemoryUnregisterRequest)
//@@ returns (SystemSharedMemoryUnregisterResponse)
//@@
//@@ Unregister a system-shared-memory region.
//@@
rpc SystemSharedMemoryUnregister(SystemSharedMemoryUnregisterRequest)
returns (SystemSharedMemoryUnregisterResponse)
{
}
//@@ .. cpp:var:: rpc CudaSharedMemoryStatus(
//@@ CudaSharedMemoryStatusRequest)
//@@ returns (CudaSharedMemoryStatusRespose)
//@@
//@@ Get the status of all registered CUDA-shared-memory regions.
//@@
rpc CudaSharedMemoryStatus(CudaSharedMemoryStatusRequest)
returns (CudaSharedMemoryStatusResponse)
{
}
//@@ .. cpp:var:: rpc CudaSharedMemoryRegister(
//@@ CudaSharedMemoryRegisterRequest)
//@@ returns (CudaSharedMemoryRegisterResponse)
//@@
//@@ Register a CUDA-shared-memory region.
//@@
rpc CudaSharedMemoryRegister(CudaSharedMemoryRegisterRequest)
returns (CudaSharedMemoryRegisterResponse)
{
}
//@@ .. cpp:var:: rpc CudaSharedMemoryUnregister(
//@@ CudaSharedMemoryUnregisterRequest)
//@@ returns (CudaSharedMemoryUnregisterResponse)
//@@
//@@ Unregister a CUDA-shared-memory region.
//@@
rpc CudaSharedMemoryUnregister(CudaSharedMemoryUnregisterRequest)
returns (CudaSharedMemoryUnregisterResponse)
{
}
//@@ .. cpp:var:: rpc TraceSetting(TraceSettingRequest)
//@@ returns (TraceSettingResponse)
//@@
//@@ Update and get the trace setting of the Triton server.
//@@
rpc TraceSetting(TraceSettingRequest) returns (TraceSettingResponse) {}
//@@ .. cpp:var:: rpc LogSettings(LogSettingsRequest)
//@@ returns (LogSettingsResponse)
//@@
//@@ Update and get the log settings of the Triton server.
//@@
rpc LogSettings(LogSettingsRequest) returns (LogSettingsResponse) {}
}
//@@
//@@.. cpp:var:: message ServerLiveRequest
//@@
//@@ Request message for ServerLive.
//@@
message ServerLiveRequest {}
//@@
//@@.. cpp:var:: message ServerLiveResponse
//@@
//@@ Response message for ServerLive.
//@@
message ServerLiveResponse
{
//@@
//@@ .. cpp:var:: bool live
//@@
//@@ True if the inference server is live, false it not live.
//@@
bool live = 1;
}
//@@
//@@.. cpp:var:: message ServerReadyRequest
//@@
//@@ Request message for ServerReady.
//@@
message ServerReadyRequest {}
//@@
//@@.. cpp:var:: message ServerReadyResponse
//@@
//@@ Response message for ServerReady.
//@@
message ServerReadyResponse
{
//@@
//@@ .. cpp:var:: bool ready
//@@
//@@ True if the inference server is ready, false it not ready.
//@@
bool ready = 1;
}
//@@
//@@.. cpp:var:: message ModelReadyRequest
//@@
//@@ Request message for ModelReady.
//@@
message ModelReadyRequest
{
//@@
//@@ .. cpp:var:: string name
//@@
//@@ The name of the model to check for readiness.
//@@
string name = 1;
//@@ .. cpp:var:: string version
//@@
//@@ The version of the model to check for readiness. If not given the
//@@ server will choose a version based on the model and internal policy.
//@@
string version = 2;
}
//@@
//@@.. cpp:var:: message ModelReadyResponse
//@@
//@@ Response message for ModelReady.
//@@
message ModelReadyResponse
{
//@@
//@@ .. cpp:var:: bool ready
//@@
//@@ True if the model is ready, false it not ready.
//@@
bool ready = 1;
}
//@@
//@@.. cpp:var:: message ServerMetadataRequest
//@@
//@@ Request message for ServerMetadata.
//@@
message ServerMetadataRequest {}
//@@
//@@.. cpp:var:: message ServerMetadataResponse
//@@
//@@ Response message for ServerMetadata.
//@@
message ServerMetadataResponse
{
//@@
//@@ .. cpp:var:: string name
//@@
//@@ The server name.
//@@
string name = 1;
//@@
//@@ .. cpp:var:: string version
//@@
//@@ The server version.
//@@
string version = 2;
//@@
//@@ .. cpp:var:: string extensions (repeated)
//@@
//@@ The extensions supported by the server.
//@@
repeated string extensions = 3;
}
//@@
//@@.. cpp:var:: message ModelMetadataRequest
//@@
//@@ Request message for ModelMetadata.
//@@
message ModelMetadataRequest
{
//@@
//@@ .. cpp:var:: string name
//@@
//@@ The name of the model.
//@@
string name = 1;
//@@ .. cpp:var:: string version
//@@
//@@ The version of the model to check for readiness. If not
//@@ given the server will choose a version based on the
//@@ model and internal policy.
//@@
string version = 2;
}
//@@
//@@.. cpp:var:: message ModelMetadataResponse
//@@
//@@ Response message for ModelMetadata.
//@@
message ModelMetadataResponse
{
//@@
//@@ .. cpp:var:: message TensorMetadata
//@@
//@@ Metadata for a tensor.
//@@
message TensorMetadata
{
//@@
//@@ .. cpp:var:: string name
//@@
//@@ The tensor name.
//@@
string name = 1;
//@@
//@@ .. cpp:var:: string datatype
//@@
//@@ The tensor data type.
//@@
string datatype = 2;
//@@
//@@ .. cpp:var:: int64 shape (repeated)
//@@
//@@ The tensor shape. A variable-size dimension is represented
//@@ by a -1 value.
//@@
repeated int64 shape = 3;
}
//@@
//@@ .. cpp:var:: string name
//@@
//@@ The model name.
//@@
string name = 1;
//@@
//@@ .. cpp:var:: string versions (repeated)
//@@
//@@ The versions of the model.
//@@
repeated string versions = 2;
//@@
//@@ .. cpp:var:: string platform
//@@
//@@ The model's platform.
//@@
string platform = 3;
//@@
//@@ .. cpp:var:: TensorMetadata inputs (repeated)
//@@
//@@ The model's inputs.
//@@
repeated TensorMetadata inputs = 4;
//@@
//@@ .. cpp:var:: TensorMetadata outputs (repeated)
//@@
//@@ The model's outputs.
//@@
repeated TensorMetadata outputs = 5;
}
//@@
//@@.. cpp:var:: message InferParameter
//@@
//@@ An inference parameter value.
//@@
message InferParameter
{
//@@ .. cpp:var:: oneof parameter_choice
//@@
//@@ The parameter value can be a string, an int64,
//@@ an uint64, a double, or a boolean
//@@
//@@ Note: double and uint64 are currently
//@@ placeholders for future use and
//@@ are not supported for custom parameters
//@@
oneof parameter_choice
{
//@@ .. cpp:var:: bool bool_param
//@@
//@@ A boolean parameter value.
//@@
bool bool_param = 1;
//@@ .. cpp:var:: int64 int64_param
//@@
//@@ An int64 parameter value.
//@@
int64 int64_param = 2;
//@@ .. cpp:var:: string string_param
//@@
//@@ A string parameter value.
//@@
string string_param = 3;
//@@ .. cpp:var:: double double_param
//@@
//@@ A double parameter value.
//@@
double double_param = 4;
//@@ .. cpp:var:: uint64 uint64_param
//@@
//@@ A uint64 parameter value.
//@@
//@@ Not supported for custom parameters
//@@
uint64 uint64_param = 5;
}
}
//@@
//@@.. cpp:var:: message InferTensorContents
//@@
//@@ The data contained in a tensor represented by the repeated type
//@@ that matches the tensor's data type. Protobuf oneof is not used
//@@ because oneofs cannot contain repeated fields.
//@@
message InferTensorContents
{
//@@
//@@ .. cpp:var:: bool bool_contents (repeated)
//@@
//@@ Representation for BOOL data type. The size must match what is
//@@ expected by the tensor's shape. The contents must be the flattened,
//@@ one-dimensional, row-major order of the tensor elements.
//@@
repeated bool bool_contents = 1;
//@@
//@@ .. cpp:var:: int32 int_contents (repeated)
//@@
//@@ Representation for INT8, INT16, and INT32 data types. The size
//@@ must match what is expected by the tensor's shape. The contents
//@@ must be the flattened, one-dimensional, row-major order of the
//@@ tensor elements.
//@@
repeated int32 int_contents = 2;
//@@
//@@ .. cpp:var:: int64 int64_contents (repeated)
//@@
//@@ Representation for INT64 data types. The size must match what
//@@ is expected by the tensor's shape. The contents must be the
//@@ flattened, one-dimensional, row-major order of the tensor elements.
//@@
repeated int64 int64_contents = 3;
//@@
//@@ .. cpp:var:: uint32 uint_contents (repeated)
//@@
//@@ Representation for UINT8, UINT16, and UINT32 data types. The size
//@@ must match what is expected by the tensor's shape. The contents
//@@ must be the flattened, one-dimensional, row-major order of the
//@@ tensor elements.
//@@
repeated uint32 uint_contents = 4;
//@@
//@@ .. cpp:var:: uint64 uint64_contents (repeated)
//@@
//@@ Representation for UINT64 data types. The size must match what
//@@ is expected by the tensor's shape. The contents must be the
//@@ flattened, one-dimensional, row-major order of the tensor elements.
//@@
repeated uint64 uint64_contents = 5;
//@@
//@@ .. cpp:var:: float fp32_contents (repeated)
//@@
//@@ Representation for FP32 data type. The size must match what is
//@@ expected by the tensor's shape. The contents must be the flattened,
//@@ one-dimensional, row-major order of the tensor elements.
//@@
repeated float fp32_contents = 6;
//@@
//@@ .. cpp:var:: double fp64_contents (repeated)
//@@
//@@ Representation for FP64 data type. The size must match what is
//@@ expected by the tensor's shape. The contents must be the flattened,
//@@ one-dimensional, row-major order of the tensor elements.
//@@
repeated double fp64_contents = 7;
//@@
//@@ .. cpp:var:: bytes bytes_contents (repeated)
//@@
//@@ Representation for BYTES data type. The size must match what is
//@@ expected by the tensor's shape. The contents must be the flattened,
//@@ one-dimensional, row-major order of the tensor elements.
//@@
repeated bytes bytes_contents = 8;
}
//@@
//@@.. cpp:var:: message ModelInferRequest
//@@
//@@ Request message for ModelInfer.
//@@
message ModelInferRequest
{
//@@
//@@ .. cpp:var:: message InferInputTensor
//@@
//@@ An input tensor for an inference request.
//@@
message InferInputTensor
{
//@@
//@@ .. cpp:var:: string name
//@@
//@@ The tensor name.
//@@
string name = 1;
//@@
//@@ .. cpp:var:: string datatype
//@@
//@@ The tensor data type.
//@@
string datatype = 2;
//@@
//@@ .. cpp:var:: int64 shape (repeated)
//@@
//@@ The tensor shape.
//@@
repeated int64 shape = 3;
//@@ .. cpp:var:: map<string,InferParameter> parameters
//@@
//@@ Optional inference input tensor parameters.
//@@
map<string, InferParameter> parameters = 4;
//@@ .. cpp:var:: InferTensorContents contents
//@@
//@@ The tensor contents using a data-type format. This field
//@@ must not be specified if tensor contents are being specified
//@@ in ModelInferRequest.raw_input_contents.
//@@
InferTensorContents contents = 5;
}
//@@
//@@ .. cpp:var:: message InferRequestedOutputTensor
//@@
//@@ An output tensor requested for an inference request.
//@@
message InferRequestedOutputTensor
{
//@@
//@@ .. cpp:var:: string name
//@@
//@@ The tensor name.
//@@
string name = 1;
//@@ .. cpp:var:: map<string,InferParameter> parameters
//@@
//@@ Optional requested output tensor parameters.
//@@
map<string, InferParameter> parameters = 2;
}
//@@ .. cpp:var:: string model_name
//@@
//@@ The name of the model to use for inferencing.
//@@
string model_name = 1;
//@@ .. cpp:var:: string model_version
//@@
//@@ The version of the model to use for inference. If not
//@@ given the latest/most-recent version of the model is used.
//@@
string model_version = 2;
//@@ .. cpp:var:: string id
//@@
//@@ Optional identifier for the request. If specified will be
//@@ returned in the response.
//@@
string id = 3;
//@@ .. cpp:var:: map<string,InferParameter> parameters
//@@
//@@ Optional inference parameters.
//@@
map<string, InferParameter> parameters = 4;
//@@
//@@ .. cpp:var:: InferInputTensor inputs (repeated)
//@@
//@@ The input tensors for the inference.
//@@
repeated InferInputTensor inputs = 5;
//@@
//@@ .. cpp:var:: InferRequestedOutputTensor outputs (repeated)
//@@
//@@ The requested output tensors for the inference. Optional, if not
//@@ specified all outputs specified in the model config will be
//@@ returned.
//@@
repeated InferRequestedOutputTensor outputs = 6;
//@@
//@@ .. cpp:var:: bytes raw_input_contents
//@@
//@@ The data contained in an input tensor can be represented in
//@@ "raw" bytes form or in the repeated type that matches the
//@@ tensor's data type. Using the "raw" bytes form will
//@@ typically allow higher performance due to the way protobuf
//@@ allocation and reuse interacts with GRPC. For example, see
//@@ https://github.com/grpc/grpc/issues/23231.
//@@
//@@ To use the raw representation 'raw_input_contents' must be
//@@ initialized with data for each tensor in the same order as
//@@ 'inputs'. For each tensor, the size of this content must
//@@ match what is expected by the tensor's shape and data
//@@ type. The raw data must be the flattened, one-dimensional,
//@@ row-major order of the tensor elements without any stride
//@@ or padding between the elements. Note that the FP16 and BF16 data
//@@ types must be represented as raw content as there is no
//@@ specific data type for a 16-bit float type.
//@@
//@@ If this field is specified then InferInputTensor::contents
//@@ must not be specified for any input tensor.
//@@
repeated bytes raw_input_contents = 7;
}
//@@
//@@.. cpp:var:: message ModelInferResponse
//@@
//@@ Response message for ModelInfer.
//@@
message ModelInferResponse
{
//@@
//@@ .. cpp:var:: message InferOutputTensor
//@@
//@@ An output tensor returned for an inference request.
//@@
message InferOutputTensor
{
//@@
//@@ .. cpp:var:: string name
//@@
//@@ The tensor name.
//@@
string name = 1;
//@@
//@@ .. cpp:var:: string datatype
//@@
//@@ The tensor data type.
//@@
string datatype = 2;
//@@
//@@ .. cpp:var:: int64 shape (repeated)
//@@
//@@ The tensor shape.
//@@
repeated int64 shape = 3;
//@@ .. cpp:var:: map<string,InferParameter> parameters
//@@
//@@ Optional output tensor parameters.
//@@
map<string, InferParameter> parameters = 4;
//@@ .. cpp:var:: InferTensorContents contents
//@@
//@@ The tensor contents using a data-type format. This field
//@@ must not be specified if tensor contents are being specified
//@@ in ModelInferResponse.raw_output_contents.
//@@
InferTensorContents contents = 5;
}
//@@ .. cpp:var:: string model_name
//@@
//@@ The name of the model used for inference.
//@@
string model_name = 1;
//@@ .. cpp:var:: string model_version
//@@
//@@ The version of the model used for inference.
//@@
string model_version = 2;
//@@ .. cpp:var:: string id
//@@
//@@ The id of the inference request if one was specified.
//@@
string id = 3;
//@@ .. cpp:var:: map<string,InferParameter> parameters
//@@
//@@ Optional inference response parameters.
//@@
map<string, InferParameter> parameters = 4;
//@@
//@@ .. cpp:var:: InferOutputTensor outputs (repeated)
//@@
//@@ The output tensors holding inference results.
//@@
repeated InferOutputTensor outputs = 5;
//@@
//@@ .. cpp:var:: bytes raw_output_contents
//@@
//@@ The data contained in an output tensor can be represented in
//@@ "raw" bytes form or in the repeated type that matches the
//@@ tensor's data type. Using the "raw" bytes form will
//@@ typically allow higher performance due to the way protobuf
//@@ allocation and reuse interacts with GRPC. For example, see
//@@ https://github.com/grpc/grpc/issues/23231.
//@@
//@@ To use the raw representation 'raw_output_contents' must be
//@@ initialized with data for each tensor in the same order as
//@@ 'outputs'. For each tensor, the size of this content must
//@@ match what is expected by the tensor's shape and data
//@@ type. The raw data must be the flattened, one-dimensional,
//@@ row-major order of the tensor elements without any stride
//@@ or padding between the elements. Note that the FP16 and BF16 data
//@@ types must be represented as raw content as there is no
//@@ specific data type for a 16-bit float type.
//@@
//@@ If this field is specified then InferOutputTensor::contents
//@@ must not be specified for any output tensor.
//@@
repeated bytes raw_output_contents = 6;
}
//@@
//@@.. cpp:var:: message ModelStreamInferResponse
//@@
//@@ Response message for ModelStreamInfer.
//@@
message ModelStreamInferResponse
{
//@@
//@@ .. cpp:var:: string error_message
//@@
//@@ The message describing the error. The empty message
//@@ indicates the inference was successful without errors.
//@@
string error_message = 1;
//@@
//@@ .. cpp:var:: ModelInferResponse infer_response
//@@
//@@ Holds the results of the request.
//@@
ModelInferResponse infer_response = 2;
}
//@@
//@@.. cpp:var:: message ModelConfigRequest
//@@
//@@ Request message for ModelConfig.
//@@
message ModelConfigRequest
{
//@@
//@@ .. cpp:var:: string name
//@@
//@@ The name of the model.
//@@
string name = 1;
//@@ .. cpp:var:: string version
//@@
//@@ The version of the model. If not given the model version
//@@ is selected automatically based on the version policy.
//@@
string version = 2;
}
//@@
//@@.. cpp:var:: message ModelConfigResponse
//@@
//@@ Response message for ModelConfig.
//@@
message ModelConfigResponse
{
//@@
//@@ .. cpp:var:: ModelConfig config
//@@
//@@ The model configuration.
//@@
ModelConfig config = 1;
}
//@@
//@@.. cpp:var:: message ModelStatisticsRequest
//@@
//@@ Request message for ModelStatistics.
//@@
message ModelStatisticsRequest
{
//@@ .. cpp:var:: string name
//@@
//@@ The name of the model. If not given returns statistics for
//@@ all models.
//@@
string name = 1;
//@@ .. cpp:var:: string version
//@@
//@@ The version of the model. If not given returns statistics for
//@@ all model versions.
//@@
string version = 2;
}
//@@
//@@.. cpp:var:: message StatisticDuration
//@@
//@@ Statistic recording a cumulative duration metric.
//@@
message StatisticDuration
{
//@@ .. cpp:var:: uint64 count
//@@
//@@ Cumulative number of times this metric occurred.
//@@
uint64 count = 1;
//@@ .. cpp:var:: uint64 total_time_ns
//@@
//@@ Total collected duration of this metric in nanoseconds.
//@@
uint64 ns = 2;
}
//@@
//@@.. cpp:var:: message InferStatistics
//@@
//@@ Inference statistics.
//@@
message InferStatistics
{
//@@ .. cpp:var:: StatisticDuration success
//@@
//@@ Cumulative count and duration for successful inference
//@@ request. The "success" count and cumulative duration includes
//@@ cache hits.
//@@
StatisticDuration success = 1;
//@@ .. cpp:var:: StatisticDuration fail
//@@
//@@ Cumulative count and duration for failed inference
//@@ request.
//@@
StatisticDuration fail = 2;
//@@ .. cpp:var:: StatisticDuration queue
//@@
//@@ The count and cumulative duration that inference requests wait in
//@@ scheduling or other queues. The "queue" count and cumulative
//@@ duration includes cache hits.
//@@
StatisticDuration queue = 3;
//@@ .. cpp:var:: StatisticDuration compute_input
//@@
//@@ The count and cumulative duration to prepare input tensor data as
//@@ required by the model framework / backend. For example, this duration
//@@ should include the time to copy input tensor data to the GPU.
//@@ The "compute_input" count and cumulative duration do not account for
//@@ requests that were a cache hit. See the "cache_hit" field for more
//@@ info.
//@@
StatisticDuration compute_input = 4;
//@@ .. cpp:var:: StatisticDuration compute_infer
//@@
//@@ The count and cumulative duration to execute the model.
//@@ The "compute_infer" count and cumulative duration do not account for
//@@ requests that were a cache hit. See the "cache_hit" field for more
//@@ info.
//@@
StatisticDuration compute_infer = 5;
//@@ .. cpp:var:: StatisticDuration compute_output
//@@
//@@ The count and cumulative duration to extract output tensor data
//@@ produced by the model framework / backend. For example, this duration
//@@ should include the time to copy output tensor data from the GPU.
//@@ The "compute_output" count and cumulative duration do not account for
//@@ requests that were a cache hit. See the "cache_hit" field for more
//@@ info.
//@@
StatisticDuration compute_output = 6;
//@@ .. cpp:var:: StatisticDuration cache_hit
//@@
//@@ The count of response cache hits and cumulative duration to lookup
//@@ and extract output tensor data from the Response Cache on a cache
//@@ hit. For example, this duration should include the time to copy
//@@ output tensor data from the Response Cache to the response object.
//@@ On cache hits, triton does not need to go to the model/backend
//@@ for the output tensor data, so the "compute_input", "compute_infer",
//@@ and "compute_output" fields are not updated. Assuming the response
//@@ cache is enabled for a given model, a cache hit occurs for a
//@@ request to that model when the request metadata (model name,
//@@ model version, model inputs) hashes to an existing entry in the
//@@ cache. On a cache miss, the request hash and response output tensor
//@@ data is added to the cache. See response cache docs for more info:
//@@
// https://github.com/triton-inference-server/server/blob/main/docs/response_cache.md
//@@
StatisticDuration cache_hit = 7;
//@@ .. cpp:var:: StatisticDuration cache_miss
//@@