Data Plane (V2)¶

$inference_request =
{
  "id" : $string #optional,
  "parameters" : $parameters #optional,
  "inputs" : [ $request_input, ... ],
  "outputs" : [ $request_output, ... ] #optional
}

$inference_request_input =
{
  "name" : $string,
  "shape" : [ $number, ... ],
  "datatype"  : $string,
  "parameters" : $parameters #optional,
  "data" : $tensor_data
}

$inference_response =
{
  "model_name" : $string,
  "model_version" : $string #optional,
  "id" : $string,
  "parameters" : $parameters #optional,
  "outputs" : [ $response_output, ... ]
}

[ 1 2
  4 5 ]

"data" : [ [ 1, 2 ], [ 4, 5 ] ]

"data" : [ 1, 2, 4, 5 ]

POST /v2/models/mymodel/infer HTTP/1.1
Host: localhost:8000
Content-Type: application/json
Content-Length: <xx>
{
  "id" : "42",
  "inputs" : [
    {
      "name" : "input0",
      "shape" : [ 2, 2 ],
      "datatype" : "UINT32",
      "data" : [ 1, 2, 3, 4 ]
    },
    {
      "name" : "input1",
      "shape" : [ 3 ],
      "datatype" : "BOOL",
      "data" : [ true ]
    }
  ],
  "outputs" : [
    {
      "name" : "output0"
    }
  ]
}

HTTP/1.1 200 OK
Content-Type: application/json
Content-Length: <yy>
{
  "id" : "42"
  "outputs" : [
    {
      "name" : "output0",
      "shape" : [ 3, 2 ],
      "datatype"  : "FP32",
      "data" : [ 1.0, 1.1, 2.0, 2.1, 3.0, 3.1 ]
    }
  ]
}

//
// Inference Server GRPC endpoints.
//
service GRPCInferenceService
{
  // Check liveness of the inference server.
  rpc ServerLive(ServerLiveRequest) returns (ServerLiveResponse) {}

  // Check readiness of the inference server.
  rpc ServerReady(ServerReadyRequest) returns (ServerReadyResponse) {}

  // Check readiness of a model in the inference server.
  rpc ModelReady(ModelReadyRequest) returns (ModelReadyResponse) {}

  // Get server metadata.
  rpc ServerMetadata(ServerMetadataRequest) returns (ServerMetadataResponse) {}

  // Get model metadata.
  rpc ModelMetadata(ModelMetadataRequest) returns (ModelMetadataResponse) {}

  // Perform inference using a specific model.
  rpc ModelInfer(ModelInferRequest) returns (ModelInferResponse) {}
}

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.
//
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;
}