forked from opendatahub-io/rest-proxy
-
Notifications
You must be signed in to change notification settings - Fork 0
/
grpc_predict_v2.proto
348 lines (281 loc) · 11.1 KB
/
grpc_predict_v2.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
// Copyright 2020 kubeflow.org.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
syntax = "proto3";
package inference;
option go_package = "./;predictv2";
import "google/api/annotations.proto";
// Inference Server GRPC endpoints.
service GRPCInferenceService
{
// The ServerLive API indicates if the inference server is able to receive
// and respond to metadata and inference requests.
rpc ServerLive(ServerLiveRequest) returns (ServerLiveResponse) {}
// The ServerReady API indicates if the server is ready for inferencing.
rpc ServerReady(ServerReadyRequest) returns (ServerReadyResponse) {}
// The ModelReady API indicates if a specific model is ready for inferencing.
rpc ModelReady(ModelReadyRequest) returns (ModelReadyResponse) {}
// The ServerMetadata API provides information about the server. Errors are
// indicated by the google.rpc.Status returned for the request. The OK code
// indicates success and other codes indicate failure.
rpc ServerMetadata(ServerMetadataRequest) returns (ServerMetadataResponse) {}
// The per-model metadata API provides information about a model. Errors are
// indicated by the google.rpc.Status returned for the request. The OK code
// indicates success and other codes indicate failure.
rpc ModelMetadata(ModelMetadataRequest) returns (ModelMetadataResponse) {
option (google.api.http) = {
get: "/v2/models/{name}"
additional_bindings {
get: "/v2/models/{name}/versions/{version}"
}
};
}
// The ModelInfer API performs inference using the specified model. Errors are
// indicated by the google.rpc.Status returned for the request. The OK code
// indicates success and other codes indicate failure.
rpc ModelInfer(ModelInferRequest) returns (ModelInferResponse) {
option (google.api.http) = {
post: "/v2/models/{model_name}/infer"
additional_bindings {
post: "/v2/models/{model_name}/versions/{model_version}/infer"
}
body: "*"
};
}
}
message ServerLiveRequest {}
message ServerLiveResponse
{
// True if the inference server is live, false if not live.
bool live = 1;
}
message ServerReadyRequest {}
message ServerReadyResponse
{
// True if the inference server is ready, false if not ready.
bool ready = 1;
}
message ModelReadyRequest
{
// The name of the model to check for readiness.
string name = 1;
// 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;
}
message ModelReadyResponse
{
// True if the model is ready, false if not ready.
bool ready = 1;
}
message ServerMetadataRequest {}
message ServerMetadataResponse
{
// The server name.
string name = 1;
// The server version.
string version = 2;
// The extensions supported by the server.
repeated string extensions = 3;
}
message ModelMetadataRequest
{
// The name of the model.
string name = 1;
// 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;
}
message ModelMetadataResponse
{
// Metadata for a tensor.
message TensorMetadata
{
// The tensor name.
string name = 1;
// The tensor data type.
string datatype = 2;
// The tensor shape. A variable-size dimension is represented
// by a -1 value.
repeated int64 shape = 3;
}
// The model name.
string name = 1;
// The versions of the model available on the server.
repeated string versions = 2;
// The model's platform. See Platforms.
string platform = 3;
// The model's inputs.
repeated TensorMetadata inputs = 4;
// The model's outputs.
repeated TensorMetadata outputs = 5;
}
message ModelInferRequest
{
// An input tensor for an inference request.
message InferInputTensor
{
// The tensor name.
string name = 1;
// The tensor data type.
string datatype = 2;
// The tensor shape.
repeated int64 shape = 3;
// Optional inference input tensor parameters.
map<string, InferParameter> parameters = 4;
// The tensor contents using a data-type format. This field must
// not be specified if "raw" tensor contents are being used for
// the inference request.
InferTensorContents contents = 5;
}
// An output tensor requested for an inference request.
message InferRequestedOutputTensor
{
// The tensor name.
string name = 1;
// Optional requested output tensor parameters.
map<string, InferParameter> parameters = 2;
}
// The name of the model to use for inferencing.
string model_name = 1;
// The version of the model to use for inference. If not given the
// server will choose a version based on the model and internal policy.
string model_version = 2;
// Optional identifier for the request. If specified will be
// returned in the response.
string id = 3;
// Optional inference parameters.
map<string, InferParameter> parameters = 4;
// The input tensors for the inference.
repeated InferInputTensor inputs = 5;
// The requested output tensors for the inference. Optional, if not
// specified all outputs produced by the model will be returned.
repeated InferRequestedOutputTensor outputs = 6;
// 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. 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 data type 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;
}
message ModelInferResponse
{
// An output tensor returned for an inference request.
message InferOutputTensor
{
// The tensor name.
string name = 1;
// The tensor data type.
string datatype = 2;
// The tensor shape.
repeated int64 shape = 3;
// Optional output tensor parameters.
map<string, InferParameter> parameters = 4;
// The tensor contents using a data-type format. This field must
// not be specified if "raw" tensor contents are being used for
// the inference response.
InferTensorContents contents = 5;
}
// The name of the model used for inference.
string model_name = 1;
// The version of the model used for inference.
string model_version = 2;
// The id of the inference request if one was specified.
string id = 3;
// Optional inference response parameters.
map<string, InferParameter> parameters = 4;
// The output tensors holding inference results.
repeated InferOutputTensor outputs = 5;
// 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. 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 data type 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;
}
// An inference parameter value. The Parameters message describes a
// “name”/”value” pair, where the “name” is the name of the parameter
// and the “value” is a boolean, integer, or string corresponding to
// the parameter.
message InferParameter
{
// The parameter value can be a string, an int64, a boolean
// or a message specific to a predefined parameter.
oneof parameter_choice
{
// A boolean parameter value.
bool bool_param = 1;
// An int64 parameter value.
int64 int64_param = 2;
// A string parameter value.
string string_param = 3;
}
}
// 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
{
// 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;
// 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;
// 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;
// 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;
// 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;
// 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;
// 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;
// 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;
}