nvidia_inferenceserver

package
v0.0.0-...-f4d7a28 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: May 28, 2019 License: Apache-2.0 Imports: 7 Imported by: 0

Documentation

Index

Constants

This section is empty.

Variables

View Source 
var DataType_name = map[int32]string{
	0:  "TYPE_INVALID",
	1:  "TYPE_BOOL",
	2:  "TYPE_UINT8",
	3:  "TYPE_UINT16",
	4:  "TYPE_UINT32",
	5:  "TYPE_UINT64",
	6:  "TYPE_INT8",
	7:  "TYPE_INT16",
	8:  "TYPE_INT32",
	9:  "TYPE_INT64",
	10: "TYPE_FP16",
	11: "TYPE_FP32",
	12: "TYPE_FP64",
	13: "TYPE_STRING",
}
View Source 
var DataType_value = map[string]int32{
	"TYPE_INVALID": 0,
	"TYPE_BOOL":    1,
	"TYPE_UINT8":   2,
	"TYPE_UINT16":  3,
	"TYPE_UINT32":  4,
	"TYPE_UINT64":  5,
	"TYPE_INT8":    6,
	"TYPE_INT16":   7,
	"TYPE_INT32":   8,
	"TYPE_INT64":   9,
	"TYPE_FP16":    10,
	"TYPE_FP32":    11,
	"TYPE_FP64":    12,
	"TYPE_STRING":  13,
}
View Source 
var InferRequestHeader_Flag_name = map[int32]string{
	0: "FLAG_NONE",
	1: "FLAG_SEQUENCE_START",
	2: "FLAG_SEQUENCE_END",
}
View Source 
var InferRequestHeader_Flag_value = map[string]int32{
	"FLAG_NONE":           0,
	"FLAG_SEQUENCE_START": 1,
	"FLAG_SEQUENCE_END":   2,
}
View Source 
var ModelInput_Format_name = map[int32]string{
	0: "FORMAT_NONE",
	1: "FORMAT_NHWC",
	2: "FORMAT_NCHW",
}
View Source 
var ModelInput_Format_value = map[string]int32{
	"FORMAT_NONE": 0,
	"FORMAT_NHWC": 1,
	"FORMAT_NCHW": 2,
}
View Source 
var ModelInstanceGroup_Kind_name = map[int32]string{
	0: "KIND_AUTO",
	1: "KIND_GPU",
	2: "KIND_CPU",
}
View Source 
var ModelInstanceGroup_Kind_value = map[string]int32{
	"KIND_AUTO": 0,
	"KIND_GPU":  1,
	"KIND_CPU":  2,
}
View Source 
var ModelOptimizationPolicy_ModelPriority_name = map[int32]string{
	0: "PRIORITY_DEFAULT",
	1: "PRIORITY_MAX",
	2: "PRIORITY_MIN",
}
View Source 
var ModelOptimizationPolicy_ModelPriority_value = map[string]int32{
	"PRIORITY_DEFAULT": 0,
	"PRIORITY_MAX":     1,
	"PRIORITY_MIN":     2,
}
View Source 
var ModelReadyState_name = map[int32]string{
	0: "MODEL_UNKNOWN",
	1: "MODEL_READY",
	2: "MODEL_UNAVAILABLE",
	3: "MODEL_LOADING",
	4: "MODEL_UNLOADING",
}
View Source 
var ModelReadyState_value = map[string]int32{
	"MODEL_UNKNOWN":     0,
	"MODEL_READY":       1,
	"MODEL_UNAVAILABLE": 2,
	"MODEL_LOADING":     3,
	"MODEL_UNLOADING":   4,
}
View Source 
var ModelSequenceBatching_Control_Kind_name = map[int32]string{
	0: "CONTROL_SEQUENCE_START",
	1: "CONTROL_SEQUENCE_READY",
}
View Source 
var ModelSequenceBatching_Control_Kind_value = map[string]int32{
	"CONTROL_SEQUENCE_START": 0,
	"CONTROL_SEQUENCE_READY": 1,
}
View Source 
var RequestStatusCode_name = map[int32]string{
	0: "INVALID",
	1: "SUCCESS",
	2: "UNKNOWN",
	3: "INTERNAL",
	4: "NOT_FOUND",
	5: "INVALID_ARG",
	6: "UNAVAILABLE",
	7: "UNSUPPORTED",
	8: "ALREADY_EXISTS",
}
View Source 
var RequestStatusCode_value = map[string]int32{
	"INVALID":        0,
	"SUCCESS":        1,
	"UNKNOWN":        2,
	"INTERNAL":       3,
	"NOT_FOUND":      4,
	"INVALID_ARG":    5,
	"UNAVAILABLE":    6,
	"UNSUPPORTED":    7,
	"ALREADY_EXISTS": 8,
}
View Source 
var ServerReadyState_name = map[int32]string{
	0:  "SERVER_INVALID",
	1:  "SERVER_INITIALIZING",
	2:  "SERVER_READY",
	3:  "SERVER_EXITING",
	10: "SERVER_FAILED_TO_INITIALIZE",
}
View Source 
var ServerReadyState_value = map[string]int32{
	"SERVER_INVALID":              0,
	"SERVER_INITIALIZING":         1,
	"SERVER_READY":                2,
	"SERVER_EXITING":              3,
	"SERVER_FAILED_TO_INITIALIZE": 10,
}

Functions

func RegisterGRPCServiceServer 

func RegisterGRPCServiceServer(s *grpc.Server, srv GRPCServiceServer)

Types

type DataType 

type DataType int32

@@ @@.. cpp:enum:: DataType @@ @@ Data types supported for input and output tensors. @@ 

const (
	//@@  .. cpp:enumerator:: DataType::INVALID = 0
	DataType_TYPE_INVALID DataType = 0
	//@@  .. cpp:enumerator:: DataType::BOOL = 1
	DataType_TYPE_BOOL DataType = 1
	//@@  .. cpp:enumerator:: DataType::UINT8 = 2
	DataType_TYPE_UINT8 DataType = 2
	//@@  .. cpp:enumerator:: DataType::UINT16 = 3
	DataType_TYPE_UINT16 DataType = 3
	//@@  .. cpp:enumerator:: DataType::UINT32 = 4
	DataType_TYPE_UINT32 DataType = 4
	//@@  .. cpp:enumerator:: DataType::UINT64 = 5
	DataType_TYPE_UINT64 DataType = 5
	//@@  .. cpp:enumerator:: DataType::INT8 = 6
	DataType_TYPE_INT8 DataType = 6
	//@@  .. cpp:enumerator:: DataType::INT16 = 7
	DataType_TYPE_INT16 DataType = 7
	//@@  .. cpp:enumerator:: DataType::INT32 = 8
	DataType_TYPE_INT32 DataType = 8
	//@@  .. cpp:enumerator:: DataType::INT64 = 9
	DataType_TYPE_INT64 DataType = 9
	//@@  .. cpp:enumerator:: DataType::FP16 = 10
	DataType_TYPE_FP16 DataType = 10
	//@@  .. cpp:enumerator:: DataType::FP32 = 11
	DataType_TYPE_FP32 DataType = 11
	//@@  .. cpp:enumerator:: DataType::FP64 = 12
	DataType_TYPE_FP64 DataType = 12
	//@@  .. cpp:enumerator:: DataType::STRING = 13
	DataType_TYPE_STRING DataType = 13
)

func (DataType) EnumDescriptor 

func (DataType) EnumDescriptor() ([]byte, []int)

func (DataType) String 

func (x DataType) String() string

type GRPCServiceClient 

type GRPCServiceClient interface {
	//@@  .. cpp:var:: rpc Status(StatusRequest) returns (StatusResponse)
	//@@
	//@@     Get status for entire inference server or for a specified model.
	//@@
	Status(ctx context.Context, in *StatusRequest, opts ...grpc.CallOption) (*StatusResponse, error)
	//@@  .. cpp:var:: rpc Profile(ProfileRequest) returns (ProfileResponse)
	//@@
	//@@     Enable and disable low-level GPU profiling.
	//@@
	Profile(ctx context.Context, in *ProfileRequest, opts ...grpc.CallOption) (*ProfileResponse, error)
	//@@  .. cpp:var:: rpc Health(HealthRequest) returns (HealthResponse)
	//@@
	//@@     Check liveness and readiness of the inference server.
	//@@
	Health(ctx context.Context, in *HealthRequest, opts ...grpc.CallOption) (*HealthResponse, error)
	//@@  .. cpp:var:: rpc Infer(InferRequest) returns (InferResponse)
	//@@
	//@@     Request inference using a specific model. [ To handle large input
	//@@     tensors likely need to set the maximum message size to that they
	//@@     can be transmitted in one pass.
	//@@
	Infer(ctx context.Context, in *InferRequest, opts ...grpc.CallOption) (*InferResponse, error)
	//@@  .. cpp:var:: rpc StreamInfer(stream InferRequest) returns (stream
	//@@     InferResponse)
	//@@
	//@@     Request inferences using a specific model in a streaming manner.
	//@@     Individual inference requests sent through the same stream will be
	//@@     processed in order and be returned on completion
	//@@
	StreamInfer(ctx context.Context, opts ...grpc.CallOption) (GRPCService_StreamInferClient, error)
}

GRPCServiceClient is the client API for GRPCService service.

For semantics around ctx use and closing/ending streaming RPCs, please refer to https://godoc.org/google.golang.org/grpc#ClientConn.NewStream.

func NewGRPCServiceClient 

func NewGRPCServiceClient(cc *grpc.ClientConn) GRPCServiceClient

type GRPCServiceServer 

type GRPCServiceServer interface {
	//@@  .. cpp:var:: rpc Status(StatusRequest) returns (StatusResponse)
	//@@
	//@@     Get status for entire inference server or for a specified model.
	//@@
	Status(context.Context, *StatusRequest) (*StatusResponse, error)
	//@@  .. cpp:var:: rpc Profile(ProfileRequest) returns (ProfileResponse)
	//@@
	//@@     Enable and disable low-level GPU profiling.
	//@@
	Profile(context.Context, *ProfileRequest) (*ProfileResponse, error)
	//@@  .. cpp:var:: rpc Health(HealthRequest) returns (HealthResponse)
	//@@
	//@@     Check liveness and readiness of the inference server.
	//@@
	Health(context.Context, *HealthRequest) (*HealthResponse, error)
	//@@  .. cpp:var:: rpc Infer(InferRequest) returns (InferResponse)
	//@@
	//@@     Request inference using a specific model. [ To handle large input
	//@@     tensors likely need to set the maximum message size to that they
	//@@     can be transmitted in one pass.
	//@@
	Infer(context.Context, *InferRequest) (*InferResponse, error)
	//@@  .. cpp:var:: rpc StreamInfer(stream InferRequest) returns (stream
	//@@     InferResponse)
	//@@
	//@@     Request inferences using a specific model in a streaming manner.
	//@@     Individual inference requests sent through the same stream will be
	//@@     processed in order and be returned on completion
	//@@
	StreamInfer(GRPCService_StreamInferServer) error
}

GRPCServiceServer is the server API for GRPCService service.

type GRPCService_StreamInferClient 

type GRPCService_StreamInferClient interface {
	Send(*InferRequest) error
	Recv() (*InferResponse, error)
	grpc.ClientStream
}

type GRPCService_StreamInferServer 

type GRPCService_StreamInferServer interface {
	Send(*InferResponse) error
	Recv() (*InferRequest, error)
	grpc.ServerStream
}

type HealthRequest 

type HealthRequest struct {
	//@@
	//@@  .. cpp:var:: string mode
	//@@
	//@@     The requested health action: 'live' requests the liveness
	//@@     state of the inference server; 'ready' requests the readiness state
	//@@     of the inference server.
	//@@
	Mode                 string   `protobuf:"bytes,1,opt,name=mode,proto3" json:"mode,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@.. cpp:var:: message HealthRequest @@ @@ Request message for Health gRPC endpoint. @@

func (*HealthRequest) Descriptor 

func (*HealthRequest) Descriptor() ([]byte, []int)

func (*HealthRequest) GetMode 

func (m *HealthRequest) GetMode() string

func (*HealthRequest) ProtoMessage 

func (*HealthRequest) ProtoMessage()

func (*HealthRequest) Reset 

func (m *HealthRequest) Reset()

func (*HealthRequest) String 

func (m *HealthRequest) String() string

func (*HealthRequest) XXX_DiscardUnknown 

func (m *HealthRequest) XXX_DiscardUnknown()

func (*HealthRequest) XXX_Marshal 

func (m *HealthRequest) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*HealthRequest) XXX_Merge 

func (m *HealthRequest) XXX_Merge(src proto.Message)

func (*HealthRequest) XXX_Size 

func (m *HealthRequest) XXX_Size() int

func (*HealthRequest) XXX_Unmarshal 

func (m *HealthRequest) XXX_Unmarshal(b []byte) error

type HealthRequestStats 

type HealthRequestStats struct {
	//@@  .. cpp:var:: StatDuration success
	//@@
	//@@     Total time required to handle successful Health requests, not
	//@@     including HTTP or gRPC endpoint termination time.
	//@@
	Success              *StatDuration `protobuf:"bytes,1,opt,name=success,proto3" json:"success,omitempty"`
	XXX_NoUnkeyedLiteral struct{}      `json:"-"`
	XXX_unrecognized     []byte        `json:"-"`
	XXX_sizecache        int32         `json:"-"`
}

@@ @@.. cpp:var:: message HealthRequestStats @@ @@ Statistics collected for Health requests. @@

func (*HealthRequestStats) Descriptor 

func (*HealthRequestStats) Descriptor() ([]byte, []int)

func (*HealthRequestStats) GetSuccess 

func (m *HealthRequestStats) GetSuccess() *StatDuration

func (*HealthRequestStats) ProtoMessage 

func (*HealthRequestStats) ProtoMessage()

func (*HealthRequestStats) Reset 

func (m *HealthRequestStats) Reset()

func (*HealthRequestStats) String 

func (m *HealthRequestStats) String() string

func (*HealthRequestStats) XXX_DiscardUnknown 

func (m *HealthRequestStats) XXX_DiscardUnknown()

func (*HealthRequestStats) XXX_Marshal 

func (m *HealthRequestStats) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*HealthRequestStats) XXX_Merge 

func (m *HealthRequestStats) XXX_Merge(src proto.Message)

func (*HealthRequestStats) XXX_Size 

func (m *HealthRequestStats) XXX_Size() int

func (*HealthRequestStats) XXX_Unmarshal 

func (m *HealthRequestStats) XXX_Unmarshal(b []byte) error

type HealthResponse 

type HealthResponse struct {
	//@@
	//@@  .. cpp:var:: RequestStatus request_status
	//@@
	//@@     The status of the request, indicating success or failure.
	//@@
	RequestStatus *RequestStatus `protobuf:"bytes,1,opt,name=request_status,json=requestStatus,proto3" json:"request_status,omitempty"`
	//@@
	//@@  .. cpp:var:: bool health
	//@@
	//@@     The result of the request. True indicates the inference server is
	//@@     live/ready, false indicates the inference server is not live/ready.
	//@@
	Health               bool     `protobuf:"varint,2,opt,name=health,proto3" json:"health,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@.. cpp:var:: message HealthResponse @@ @@ Response message for Health gRPC endpoint. @@

func (*HealthResponse) Descriptor 

func (*HealthResponse) Descriptor() ([]byte, []int)

func (*HealthResponse) GetHealth 

func (m *HealthResponse) GetHealth() bool

func (*HealthResponse) GetRequestStatus 

func (m *HealthResponse) GetRequestStatus() *RequestStatus

func (*HealthResponse) ProtoMessage 

func (*HealthResponse) ProtoMessage()

func (*HealthResponse) Reset 

func (m *HealthResponse) Reset()

func (*HealthResponse) String 

func (m *HealthResponse) String() string

func (*HealthResponse) XXX_DiscardUnknown 

func (m *HealthResponse) XXX_DiscardUnknown()

func (*HealthResponse) XXX_Marshal 

func (m *HealthResponse) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*HealthResponse) XXX_Merge 

func (m *HealthResponse) XXX_Merge(src proto.Message)

func (*HealthResponse) XXX_Size 

func (m *HealthResponse) XXX_Size() int

func (*HealthResponse) XXX_Unmarshal 

func (m *HealthResponse) XXX_Unmarshal(b []byte) error

type InferRequest 

type InferRequest struct {
	//@@  .. cpp:var:: string model_name
	//@@
	//@@     The name of the model to use for inferencing.
	//@@
	ModelName string `protobuf:"bytes,1,opt,name=model_name,json=modelName,proto3" json:"model_name,omitempty"`
	//@@  .. cpp:var:: int64 version
	//@@
	//@@     The version of the model to use for inference. If -1
	//@@     the latest/most-recent version of the model is used.
	//@@
	ModelVersion int64 `protobuf:"varint,2,opt,name=model_version,json=modelVersion,proto3" json:"model_version,omitempty"`
	//@@  .. cpp:var:: InferRequestHeader meta_data
	//@@
	//@@     Meta-data for the request profiling input tensors and requesting
	//@@     output tensors.
	//@@
	MetaData *InferRequestHeader `protobuf:"bytes,3,opt,name=meta_data,json=metaData,proto3" json:"meta_data,omitempty"`
	//@@  .. cpp:var:: bytes raw_input (repeated)
	//@@
	//@@     The raw input tensor data in the order specified in 'meta_data'.
	//@@
	RawInput             [][]byte `protobuf:"bytes,4,rep,name=raw_input,json=rawInput,proto3" json:"raw_input,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@.. cpp:var:: message InferRequest @@ @@ Request message for Infer gRPC endpoint. @@

func (*InferRequest) Descriptor 

func (*InferRequest) Descriptor() ([]byte, []int)

func (*InferRequest) GetMetaData 

func (m *InferRequest) GetMetaData() *InferRequestHeader

func (*InferRequest) GetModelName 

func (m *InferRequest) GetModelName() string

func (*InferRequest) GetModelVersion 

func (m *InferRequest) GetModelVersion() int64

func (*InferRequest) GetRawInput 

func (m *InferRequest) GetRawInput() [][]byte

func (*InferRequest) ProtoMessage 

func (*InferRequest) ProtoMessage()

func (*InferRequest) Reset 

func (m *InferRequest) Reset()

func (*InferRequest) String 

func (m *InferRequest) String() string

func (*InferRequest) XXX_DiscardUnknown 

func (m *InferRequest) XXX_DiscardUnknown()

func (*InferRequest) XXX_Marshal 

func (m *InferRequest) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*InferRequest) XXX_Merge 

func (m *InferRequest) XXX_Merge(src proto.Message)

func (*InferRequest) XXX_Size 

func (m *InferRequest) XXX_Size() int

func (*InferRequest) XXX_Unmarshal 

func (m *InferRequest) XXX_Unmarshal(b []byte) error

type InferRequestHeader 

type InferRequestHeader struct {
	//@@  .. cpp:var:: uint64 id
	//@@
	//@@     The ID of the inference request. The response of the request will
	//@@     have the same ID in InferResponseHeader. The request sender can use
	//@@     the ID to correlate the response to corresponding request if needed.
	//@@
	Id uint64 `protobuf:"varint,5,opt,name=id,proto3" json:"id,omitempty"`
	//@@  .. cpp:var:: uint32 flags
	//@@
	//@@     The flags associated with this request. This field holds a bitwise-or
	//@@     of all flag values.
	//@@
	Flags uint32 `protobuf:"varint,6,opt,name=flags,proto3" json:"flags,omitempty"`
	//@@  .. cpp:var:: uint64 correlation_id
	//@@
	//@@     The correlation ID of the inference request. Default is 0, which
	//@@     indictes that the request has no correlation ID. The correlation ID
	//@@     is used to indicate two or more inference request are related to
	//@@     each other. How this relationship is handled by the inference
	//@@     server is determined by the model's scheduling policy.
	//@@
	CorrelationId uint64 `protobuf:"varint,4,opt,name=correlation_id,json=correlationId,proto3" json:"correlation_id,omitempty"`
	//@@  .. cpp:var:: uint32 batch_size
	//@@
	//@@     The batch size of the inference request. This must be >= 1. For
	//@@     models that don't support batching, batch_size must be 1.
	//@@
	BatchSize uint32 `protobuf:"varint,1,opt,name=batch_size,json=batchSize,proto3" json:"batch_size,omitempty"`
	//@@  .. cpp:var:: Input input (repeated)
	//@@
	//@@     The input meta-data for the inputs provided with the the inference
	//@@     request.
	//@@
	Input []*InferRequestHeader_Input `protobuf:"bytes,2,rep,name=input,proto3" json:"input,omitempty"`
	//@@  .. cpp:var:: Output output (repeated)
	//@@
	//@@     The output meta-data for the inputs provided with the the inference
	//@@     request.
	//@@
	Output               []*InferRequestHeader_Output `protobuf:"bytes,3,rep,name=output,proto3" json:"output,omitempty"`
	XXX_NoUnkeyedLiteral struct{}                     `json:"-"`
	XXX_unrecognized     []byte                       `json:"-"`
	XXX_sizecache        int32                        `json:"-"`
}

@@ @@.. cpp:var:: message InferRequestHeader @@ @@ Meta-data for an inferencing request. The actual input data is @@ delivered separate from this header, in the HTTP body for an HTTP @@ request, or in the :cpp:var:`InferRequest` message for a gRPC request. @@

func (*InferRequestHeader) Descriptor 

func (*InferRequestHeader) Descriptor() ([]byte, []int)

func (*InferRequestHeader) GetBatchSize 

func (m *InferRequestHeader) GetBatchSize() uint32

func (*InferRequestHeader) GetCorrelationId 

func (m *InferRequestHeader) GetCorrelationId() uint64

func (*InferRequestHeader) GetFlags 

func (m *InferRequestHeader) GetFlags() uint32

func (*InferRequestHeader) GetId 

func (m *InferRequestHeader) GetId() uint64

func (*InferRequestHeader) GetInput 

func (m *InferRequestHeader) GetInput() []*InferRequestHeader_Input

func (*InferRequestHeader) GetOutput 

func (m *InferRequestHeader) GetOutput() []*InferRequestHeader_Output

func (*InferRequestHeader) ProtoMessage 

func (*InferRequestHeader) ProtoMessage()

func (*InferRequestHeader) Reset 

func (m *InferRequestHeader) Reset()

func (*InferRequestHeader) String 

func (m *InferRequestHeader) String() string

func (*InferRequestHeader) XXX_DiscardUnknown 

func (m *InferRequestHeader) XXX_DiscardUnknown()

func (*InferRequestHeader) XXX_Marshal 

func (m *InferRequestHeader) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*InferRequestHeader) XXX_Merge 

func (m *InferRequestHeader) XXX_Merge(src proto.Message)

func (*InferRequestHeader) XXX_Size 

func (m *InferRequestHeader) XXX_Size() int

func (*InferRequestHeader) XXX_Unmarshal 

func (m *InferRequestHeader) XXX_Unmarshal(b []byte) error

type InferRequestHeader_Flag 

type InferRequestHeader_Flag int32

@@ .. cpp:enum:: Flag @@ @@ Flags that can be associated with an inference request. @@ All flags are packed bitwise into the 'flags' field and @@ so the value of each must be a power-of-2. @@ 

const (
	//@@    .. cpp:enumerator:: Flag::FLAG_NONE = 0
	//@@
	//@@       Value indicating no flags are enabled.
	//@@
	InferRequestHeader_FLAG_NONE InferRequestHeader_Flag = 0
	//@@    .. cpp:enumerator:: Flag::FLAG_SEQUENCE_START = 1 << 0
	//@@
	//@@       This request is the start of a related sequence of requests.
	//@@
	InferRequestHeader_FLAG_SEQUENCE_START InferRequestHeader_Flag = 1
	//@@    .. cpp:enumerator:: Flag::FLAG_SEQUENCE_END = 1 << 1
	//@@
	//@@       This request is the end of a related sequence of requests.
	//@@
	InferRequestHeader_FLAG_SEQUENCE_END InferRequestHeader_Flag = 2
)

func (InferRequestHeader_Flag) EnumDescriptor 

func (InferRequestHeader_Flag) EnumDescriptor() ([]byte, []int)

func (InferRequestHeader_Flag) String 

func (x InferRequestHeader_Flag) String() string

type InferRequestHeader_Input 

type InferRequestHeader_Input struct {
	//@@    .. cpp:var:: string name
	//@@
	//@@       The name of the input tensor.
	//@@
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	//@@    .. cpp:var:: int64 dims (repeated)
	//@@
	//@@       The shape of the input tensor, not including the batch dimension.
	//@@       Optional if the model configuration for this input explicitly
	//@@       specifies all dimensions of the shape. Required if the model
	//@@       configuration for this input has any wildcard dimensions (-1).
	//@@
	Dims []int64 `protobuf:"varint,2,rep,packed,name=dims,proto3" json:"dims,omitempty"`
	//@@    .. cpp:var:: uint64 batch_byte_size
	//@@
	//@@       The size of the full batch of the input tensor, in bytes.
	//@@       Optional for tensors with fixed-sized datatypes. Required
	//@@       for tensors with a non-fixed-size datatype (like STRING).
	//@@
	BatchByteSize        uint64   `protobuf:"varint,3,opt,name=batch_byte_size,json=batchByteSize,proto3" json:"batch_byte_size,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ .. cpp:var:: message Input @@ @@ Meta-data for an input tensor provided as part of an inferencing @@ request. @@

func (*InferRequestHeader_Input) Descriptor 

func (*InferRequestHeader_Input) Descriptor() ([]byte, []int)

func (*InferRequestHeader_Input) GetBatchByteSize 

func (m *InferRequestHeader_Input) GetBatchByteSize() uint64

func (*InferRequestHeader_Input) GetDims 

func (m *InferRequestHeader_Input) GetDims() []int64

func (*InferRequestHeader_Input) GetName 

func (m *InferRequestHeader_Input) GetName() string

func (*InferRequestHeader_Input) ProtoMessage 

func (*InferRequestHeader_Input) ProtoMessage()

func (*InferRequestHeader_Input) Reset 

func (m *InferRequestHeader_Input) Reset()

func (*InferRequestHeader_Input) String 

func (m *InferRequestHeader_Input) String() string

func (*InferRequestHeader_Input) XXX_DiscardUnknown 

func (m *InferRequestHeader_Input) XXX_DiscardUnknown()

func (*InferRequestHeader_Input) XXX_Marshal 

func (m *InferRequestHeader_Input) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*InferRequestHeader_Input) XXX_Merge 

func (m *InferRequestHeader_Input) XXX_Merge(src proto.Message)

func (*InferRequestHeader_Input) XXX_Size 

func (m *InferRequestHeader_Input) XXX_Size() int

func (*InferRequestHeader_Input) XXX_Unmarshal 

func (m *InferRequestHeader_Input) XXX_Unmarshal(b []byte) error

type InferRequestHeader_Output 

type InferRequestHeader_Output struct {
	//@@    .. cpp:var:: string name
	//@@
	//@@       The name of the output tensor.
	//@@
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	//@@    .. cpp:var:: Class cls
	//@@
	//@@       Optional. If defined return this output as a classification
	//@@       instead of raw data. The output tensor will be interpreted as
	//@@       probabilities and the classifications associated with the
	//@@       highest probabilities will be returned.
	//@@
	Cls                  *InferRequestHeader_Output_Class `protobuf:"bytes,3,opt,name=cls,proto3" json:"cls,omitempty"`
	XXX_NoUnkeyedLiteral struct{}                         `json:"-"`
	XXX_unrecognized     []byte                           `json:"-"`
	XXX_sizecache        int32                            `json:"-"`
}

@@ .. cpp:var:: message Output @@ @@ Meta-data for a requested output tensor as part of an inferencing @@ request. @@

func (*InferRequestHeader_Output) Descriptor 

func (*InferRequestHeader_Output) Descriptor() ([]byte, []int)

func (*InferRequestHeader_Output) GetCls 

func (m *InferRequestHeader_Output) GetCls() *InferRequestHeader_Output_Class

func (*InferRequestHeader_Output) GetName 

func (m *InferRequestHeader_Output) GetName() string

func (*InferRequestHeader_Output) ProtoMessage 

func (*InferRequestHeader_Output) ProtoMessage()

func (*InferRequestHeader_Output) Reset 

func (m *InferRequestHeader_Output) Reset()

func (*InferRequestHeader_Output) String 

func (m *InferRequestHeader_Output) String() string

func (*InferRequestHeader_Output) XXX_DiscardUnknown 

func (m *InferRequestHeader_Output) XXX_DiscardUnknown()

func (*InferRequestHeader_Output) XXX_Marshal 

func (m *InferRequestHeader_Output) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*InferRequestHeader_Output) XXX_Merge 

func (m *InferRequestHeader_Output) XXX_Merge(src proto.Message)

func (*InferRequestHeader_Output) XXX_Size 

func (m *InferRequestHeader_Output) XXX_Size() int

func (*InferRequestHeader_Output) XXX_Unmarshal 

func (m *InferRequestHeader_Output) XXX_Unmarshal(b []byte) error

type InferRequestHeader_Output_Class 

type InferRequestHeader_Output_Class struct {
	//@@      .. cpp:var:: uint32 count
	//@@
	//@@         Indicates how many classification values should be returned
	//@@         for the output. The 'count' highest priority values are
	//@@         returned.
	//@@
	Count                uint32   `protobuf:"varint,1,opt,name=count,proto3" json:"count,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ .. cpp:var:: message Class @@ @@ Options for an output returned as a classification. @@

func (*InferRequestHeader_Output_Class) Descriptor 

func (*InferRequestHeader_Output_Class) Descriptor() ([]byte, []int)

func (*InferRequestHeader_Output_Class) GetCount 

func (m *InferRequestHeader_Output_Class) GetCount() uint32

func (*InferRequestHeader_Output_Class) ProtoMessage 

func (*InferRequestHeader_Output_Class) ProtoMessage()

func (*InferRequestHeader_Output_Class) Reset 

func (m *InferRequestHeader_Output_Class) Reset()

func (*InferRequestHeader_Output_Class) String 

func (m *InferRequestHeader_Output_Class) String() string

func (*InferRequestHeader_Output_Class) XXX_DiscardUnknown 

func (m *InferRequestHeader_Output_Class) XXX_DiscardUnknown()

func (*InferRequestHeader_Output_Class) XXX_Marshal 

func (m *InferRequestHeader_Output_Class) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*InferRequestHeader_Output_Class) XXX_Merge 

func (m *InferRequestHeader_Output_Class) XXX_Merge(src proto.Message)

func (*InferRequestHeader_Output_Class) XXX_Size 

func (m *InferRequestHeader_Output_Class) XXX_Size() int

func (*InferRequestHeader_Output_Class) XXX_Unmarshal 

func (m *InferRequestHeader_Output_Class) XXX_Unmarshal(b []byte) error

type InferRequestStats 

type InferRequestStats struct {
	//@@  .. cpp:var:: StatDuration success
	//@@
	//@@     Total time required to handle successful Infer requests, not
	//@@     including HTTP or gRPC endpoint termination time.
	//@@
	Success *StatDuration `protobuf:"bytes,1,opt,name=success,proto3" json:"success,omitempty"`
	//@@  .. cpp:var:: StatDuration failed
	//@@
	//@@     Total time required to handle failed Infer requests, not
	//@@     including HTTP or gRPC endpoint termination time.
	//@@
	Failed *StatDuration `protobuf:"bytes,2,opt,name=failed,proto3" json:"failed,omitempty"`
	//@@  .. cpp:var:: StatDuration compute
	//@@
	//@@     Time required to run inferencing for an inference request;
	//@@     including time copying input tensors to GPU memory, time
	//@@     executing the model, and time copying output tensors from GPU
	//@@     memory.
	//@@
	Compute *StatDuration `protobuf:"bytes,3,opt,name=compute,proto3" json:"compute,omitempty"`
	//@@  .. cpp:var:: StatDuration queue
	//@@
	//@@     Time an inference request waits in scheduling queue for an
	//@@     available model instance.
	//@@
	Queue                *StatDuration `protobuf:"bytes,4,opt,name=queue,proto3" json:"queue,omitempty"`
	XXX_NoUnkeyedLiteral struct{}      `json:"-"`
	XXX_unrecognized     []byte        `json:"-"`
	XXX_sizecache        int32         `json:"-"`
}

@@ @@.. cpp:var:: message InferRequestStats @@ @@ Statistics collected for Infer requests. @@

func (*InferRequestStats) Descriptor 

func (*InferRequestStats) Descriptor() ([]byte, []int)

func (*InferRequestStats) GetCompute 

func (m *InferRequestStats) GetCompute() *StatDuration

func (*InferRequestStats) GetFailed 

func (m *InferRequestStats) GetFailed() *StatDuration

func (*InferRequestStats) GetQueue 

func (m *InferRequestStats) GetQueue() *StatDuration

func (*InferRequestStats) GetSuccess 

func (m *InferRequestStats) GetSuccess() *StatDuration

func (*InferRequestStats) ProtoMessage 

func (*InferRequestStats) ProtoMessage()

func (*InferRequestStats) Reset 

func (m *InferRequestStats) Reset()

func (*InferRequestStats) String 

func (m *InferRequestStats) String() string

func (*InferRequestStats) XXX_DiscardUnknown 

func (m *InferRequestStats) XXX_DiscardUnknown()

func (*InferRequestStats) XXX_Marshal 

func (m *InferRequestStats) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*InferRequestStats) XXX_Merge 

func (m *InferRequestStats) XXX_Merge(src proto.Message)

func (*InferRequestStats) XXX_Size 

func (m *InferRequestStats) XXX_Size() int

func (*InferRequestStats) XXX_Unmarshal 

func (m *InferRequestStats) XXX_Unmarshal(b []byte) error

type InferResponse 

type InferResponse struct {
	//@@
	//@@  .. cpp:var:: RequestStatus request_status
	//@@
	//@@     The status of the request, indicating success or failure.
	//@@
	RequestStatus *RequestStatus `protobuf:"bytes,1,opt,name=request_status,json=requestStatus,proto3" json:"request_status,omitempty"`
	//@@  .. cpp:var:: InferResponseHeader meta_data
	//@@
	//@@     The response meta-data for the output tensors.
	//@@
	MetaData *InferResponseHeader `protobuf:"bytes,2,opt,name=meta_data,json=metaData,proto3" json:"meta_data,omitempty"`
	//@@  .. cpp:var:: bytes raw_output (repeated)
	//@@
	//@@     The raw output tensor data in the order specified in 'meta_data'.
	//@@
	RawOutput            [][]byte `protobuf:"bytes,3,rep,name=raw_output,json=rawOutput,proto3" json:"raw_output,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@.. cpp:var:: message InferResponse @@ @@ Response message for Infer gRPC endpoint. @@

func (*InferResponse) Descriptor 

func (*InferResponse) Descriptor() ([]byte, []int)

func (*InferResponse) GetMetaData 

func (m *InferResponse) GetMetaData() *InferResponseHeader

func (*InferResponse) GetRawOutput 

func (m *InferResponse) GetRawOutput() [][]byte

func (*InferResponse) GetRequestStatus 

func (m *InferResponse) GetRequestStatus() *RequestStatus

func (*InferResponse) ProtoMessage 

func (*InferResponse) ProtoMessage()

func (*InferResponse) Reset 

func (m *InferResponse) Reset()

func (*InferResponse) String 

func (m *InferResponse) String() string

func (*InferResponse) XXX_DiscardUnknown 

func (m *InferResponse) XXX_DiscardUnknown()

func (*InferResponse) XXX_Marshal 

func (m *InferResponse) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*InferResponse) XXX_Merge 

func (m *InferResponse) XXX_Merge(src proto.Message)

func (*InferResponse) XXX_Size 

func (m *InferResponse) XXX_Size() int

func (*InferResponse) XXX_Unmarshal 

func (m *InferResponse) XXX_Unmarshal(b []byte) error

type InferResponseHeader 

type InferResponseHeader struct {
	//@@  .. cpp:var:: uint64 id
	//@@
	//@@     The ID of the inference response. The response will have the same ID
	//@@     as the ID of its originated request. The request sender can use
	//@@     the ID to correlate the response to corresponding request if needed.
	//@@
	Id uint64 `protobuf:"varint,5,opt,name=id,proto3" json:"id,omitempty"`
	//@@  .. cpp:var:: string model_name
	//@@
	//@@     The name of the model that produced the outputs.
	//@@
	ModelName string `protobuf:"bytes,1,opt,name=model_name,json=modelName,proto3" json:"model_name,omitempty"`
	//@@  .. cpp:var:: int64 model_version
	//@@
	//@@     The version of the model that produced the outputs.
	//@@
	ModelVersion int64 `protobuf:"varint,2,opt,name=model_version,json=modelVersion,proto3" json:"model_version,omitempty"`
	//@@  .. cpp:var:: uint32 batch_size
	//@@
	//@@     The batch size of the outputs. This will always be equal to the
	//@@     batch size of the inputs. For models that don't support
	//@@     batching the batch_size will be 1.
	//@@
	BatchSize uint32 `protobuf:"varint,3,opt,name=batch_size,json=batchSize,proto3" json:"batch_size,omitempty"`
	//@@  .. cpp:var:: Output output (repeated)
	//@@
	//@@     The outputs, in the same order as they were requested in
	//@@     :cpp:var:`InferRequestHeader`.
	//@@
	Output               []*InferResponseHeader_Output `protobuf:"bytes,4,rep,name=output,proto3" json:"output,omitempty"`
	XXX_NoUnkeyedLiteral struct{}                      `json:"-"`
	XXX_unrecognized     []byte                        `json:"-"`
	XXX_sizecache        int32                         `json:"-"`
}

@@ @@.. cpp:var:: message InferResponseHeader @@ @@ Meta-data for the response to an inferencing request. The actual output @@ data is delivered separate from this header, in the HTTP body for an HTTP @@ request, or in the :cpp:var:`InferResponse` message for a gRPC request. @@

func (*InferResponseHeader) Descriptor 

func (*InferResponseHeader) Descriptor() ([]byte, []int)

func (*InferResponseHeader) GetBatchSize 

func (m *InferResponseHeader) GetBatchSize() uint32

func (*InferResponseHeader) GetId 

func (m *InferResponseHeader) GetId() uint64

func (*InferResponseHeader) GetModelName 

func (m *InferResponseHeader) GetModelName() string

func (*InferResponseHeader) GetModelVersion 

func (m *InferResponseHeader) GetModelVersion() int64

func (*InferResponseHeader) GetOutput 

func (m *InferResponseHeader) GetOutput() []*InferResponseHeader_Output

func (*InferResponseHeader) ProtoMessage 

func (*InferResponseHeader) ProtoMessage()

func (*InferResponseHeader) Reset 

func (m *InferResponseHeader) Reset()

func (*InferResponseHeader) String 

func (m *InferResponseHeader) String() string

func (*InferResponseHeader) XXX_DiscardUnknown 

func (m *InferResponseHeader) XXX_DiscardUnknown()

func (*InferResponseHeader) XXX_Marshal 

func (m *InferResponseHeader) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*InferResponseHeader) XXX_Merge 

func (m *InferResponseHeader) XXX_Merge(src proto.Message)

func (*InferResponseHeader) XXX_Size 

func (m *InferResponseHeader) XXX_Size() int

func (*InferResponseHeader) XXX_Unmarshal 

func (m *InferResponseHeader) XXX_Unmarshal(b []byte) error

type InferResponseHeader_Output 

type InferResponseHeader_Output struct {
	//@@    .. cpp:var:: string name
	//@@
	//@@       The name of the output tensor.
	//@@
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	//@@    .. cpp:var:: Raw raw
	//@@
	//@@       If specified deliver results for this output as raw tensor data.
	//@@       The actual output data is delivered in the HTTP body for an HTTP
	//@@       request, or in the :cpp:var:`InferResponse` message for a gRPC
	//@@       request. Only one of 'raw' and 'batch_classes' may be specified.
	//@@
	Raw *InferResponseHeader_Output_Raw `protobuf:"bytes,2,opt,name=raw,proto3" json:"raw,omitempty"`
	//@@    .. cpp:var:: Classes batch_classes (repeated)
	//@@
	//@@       If specified deliver results for this output as classifications.
	//@@       There is one :cpp:var:`Classes` object for each batch entry in
	//@@       the output. Only one of 'raw' and 'batch_classes' may be
	//@@       specified.
	//@@
	BatchClasses         []*InferResponseHeader_Output_Classes `protobuf:"bytes,3,rep,name=batch_classes,json=batchClasses,proto3" json:"batch_classes,omitempty"`
	XXX_NoUnkeyedLiteral struct{}                              `json:"-"`
	XXX_unrecognized     []byte                                `json:"-"`
	XXX_sizecache        int32                                 `json:"-"`
}

@@ .. cpp:var:: message Output @@ @@ Meta-data for an output tensor requested as part of an inferencing @@ request. @@

func (*InferResponseHeader_Output) Descriptor 

func (*InferResponseHeader_Output) Descriptor() ([]byte, []int)

func (*InferResponseHeader_Output) GetBatchClasses 

func (m *InferResponseHeader_Output) GetBatchClasses() []*InferResponseHeader_Output_Classes

func (*InferResponseHeader_Output) GetName 

func (m *InferResponseHeader_Output) GetName() string

func (*InferResponseHeader_Output) GetRaw 

func (m *InferResponseHeader_Output) GetRaw() *InferResponseHeader_Output_Raw

func (*InferResponseHeader_Output) ProtoMessage 

func (*InferResponseHeader_Output) ProtoMessage()

func (*InferResponseHeader_Output) Reset 

func (m *InferResponseHeader_Output) Reset()

func (*InferResponseHeader_Output) String 

func (m *InferResponseHeader_Output) String() string

func (*InferResponseHeader_Output) XXX_DiscardUnknown 

func (m *InferResponseHeader_Output) XXX_DiscardUnknown()

func (*InferResponseHeader_Output) XXX_Marshal 

func (m *InferResponseHeader_Output) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*InferResponseHeader_Output) XXX_Merge 

func (m *InferResponseHeader_Output) XXX_Merge(src proto.Message)

func (*InferResponseHeader_Output) XXX_Size 

func (m *InferResponseHeader_Output) XXX_Size() int

func (*InferResponseHeader_Output) XXX_Unmarshal 

func (m *InferResponseHeader_Output) XXX_Unmarshal(b []byte) error

type InferResponseHeader_Output_Class 

type InferResponseHeader_Output_Class struct {
	//@@      .. cpp:var:: int32 idx
	//@@
	//@@         The classification index.
	//@@
	Idx int32 `protobuf:"varint,1,opt,name=idx,proto3" json:"idx,omitempty"`
	//@@      .. cpp:var:: float value
	//@@
	//@@         The classification value as a float (typically a
	//@@         probability).
	//@@
	Value float32 `protobuf:"fixed32,2,opt,name=value,proto3" json:"value,omitempty"`
	//@@      .. cpp:var:: string label
	//@@
	//@@         The label for the class (optional, only available if provided
	//@@         by the model).
	//@@
	Label                string   `protobuf:"bytes,3,opt,name=label,proto3" json:"label,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ .. cpp:var:: message Class @@ @@ Information about each classification for this output. @@

func (*InferResponseHeader_Output_Class) Descriptor 

func (*InferResponseHeader_Output_Class) Descriptor() ([]byte, []int)

func (*InferResponseHeader_Output_Class) GetIdx 

func (m *InferResponseHeader_Output_Class) GetIdx() int32

func (*InferResponseHeader_Output_Class) GetLabel 

func (m *InferResponseHeader_Output_Class) GetLabel() string

func (*InferResponseHeader_Output_Class) GetValue 

func (m *InferResponseHeader_Output_Class) GetValue() float32

func (*InferResponseHeader_Output_Class) ProtoMessage 

func (*InferResponseHeader_Output_Class) ProtoMessage()

func (*InferResponseHeader_Output_Class) Reset 

func (m *InferResponseHeader_Output_Class) Reset()

func (*InferResponseHeader_Output_Class) String 

func (m *InferResponseHeader_Output_Class) String() string

func (*InferResponseHeader_Output_Class) XXX_DiscardUnknown 

func (m *InferResponseHeader_Output_Class) XXX_DiscardUnknown()

func (*InferResponseHeader_Output_Class) XXX_Marshal 

func (m *InferResponseHeader_Output_Class) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*InferResponseHeader_Output_Class) XXX_Merge 

func (m *InferResponseHeader_Output_Class) XXX_Merge(src proto.Message)

func (*InferResponseHeader_Output_Class) XXX_Size 

func (m *InferResponseHeader_Output_Class) XXX_Size() int

func (*InferResponseHeader_Output_Class) XXX_Unmarshal 

func (m *InferResponseHeader_Output_Class) XXX_Unmarshal(b []byte) error

type InferResponseHeader_Output_Classes 

type InferResponseHeader_Output_Classes struct {
	//@@      .. cpp:var:: Class cls (repeated)
	//@@
	//@@         The topk classes for this output.
	//@@
	Cls                  []*InferResponseHeader_Output_Class `protobuf:"bytes,1,rep,name=cls,proto3" json:"cls,omitempty"`
	XXX_NoUnkeyedLiteral struct{}                            `json:"-"`
	XXX_unrecognized     []byte                              `json:"-"`
	XXX_sizecache        int32                               `json:"-"`
}

@@ .. cpp:var:: message Classes @@ @@ Meta-data for an output tensor being returned as classifications. @@

func (*InferResponseHeader_Output_Classes) Descriptor 

func (*InferResponseHeader_Output_Classes) Descriptor() ([]byte, []int)

func (*InferResponseHeader_Output_Classes) GetCls 

func (m *InferResponseHeader_Output_Classes) GetCls() []*InferResponseHeader_Output_Class

func (*InferResponseHeader_Output_Classes) ProtoMessage 

func (*InferResponseHeader_Output_Classes) ProtoMessage()

func (*InferResponseHeader_Output_Classes) Reset 

func (m *InferResponseHeader_Output_Classes) Reset()

func (*InferResponseHeader_Output_Classes) String 

func (m *InferResponseHeader_Output_Classes) String() string

func (*InferResponseHeader_Output_Classes) XXX_DiscardUnknown 

func (m *InferResponseHeader_Output_Classes) XXX_DiscardUnknown()

func (*InferResponseHeader_Output_Classes) XXX_Marshal 

func (m *InferResponseHeader_Output_Classes) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*InferResponseHeader_Output_Classes) XXX_Merge 

func (m *InferResponseHeader_Output_Classes) XXX_Merge(src proto.Message)

func (*InferResponseHeader_Output_Classes) XXX_Size 

func (m *InferResponseHeader_Output_Classes) XXX_Size() int

func (*InferResponseHeader_Output_Classes) XXX_Unmarshal 

func (m *InferResponseHeader_Output_Classes) XXX_Unmarshal(b []byte) error

type InferResponseHeader_Output_Raw 

type InferResponseHeader_Output_Raw struct {
	//@@      .. cpp:var:: int64 dims (repeated)
	//@@
	//@@         The shape of the output tensor, not including the batch
	//@@         dimension.
	//@@
	Dims []int64 `protobuf:"varint,1,rep,packed,name=dims,proto3" json:"dims,omitempty"`
	//@@      .. cpp:var:: uint64 batch_byte_size
	//@@
	//@@         The full size of the output tensor, in bytes. For a
	//@@         batch output, this is the size of the entire batch.
	//@@
	BatchByteSize        uint64   `protobuf:"varint,2,opt,name=batch_byte_size,json=batchByteSize,proto3" json:"batch_byte_size,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ .. cpp:var:: message Raw @@ @@ Meta-data for an output tensor being returned as raw data. @@

func (*InferResponseHeader_Output_Raw) Descriptor 

func (*InferResponseHeader_Output_Raw) Descriptor() ([]byte, []int)

func (*InferResponseHeader_Output_Raw) GetBatchByteSize 

func (m *InferResponseHeader_Output_Raw) GetBatchByteSize() uint64

func (*InferResponseHeader_Output_Raw) GetDims 

func (m *InferResponseHeader_Output_Raw) GetDims() []int64

func (*InferResponseHeader_Output_Raw) ProtoMessage 

func (*InferResponseHeader_Output_Raw) ProtoMessage()

func (*InferResponseHeader_Output_Raw) Reset 

func (m *InferResponseHeader_Output_Raw) Reset()

func (*InferResponseHeader_Output_Raw) String 

func (m *InferResponseHeader_Output_Raw) String() string

func (*InferResponseHeader_Output_Raw) XXX_DiscardUnknown 

func (m *InferResponseHeader_Output_Raw) XXX_DiscardUnknown()

func (*InferResponseHeader_Output_Raw) XXX_Marshal 

func (m *InferResponseHeader_Output_Raw) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*InferResponseHeader_Output_Raw) XXX_Merge 

func (m *InferResponseHeader_Output_Raw) XXX_Merge(src proto.Message)

func (*InferResponseHeader_Output_Raw) XXX_Size 

func (m *InferResponseHeader_Output_Raw) XXX_Size() int

func (*InferResponseHeader_Output_Raw) XXX_Unmarshal 

func (m *InferResponseHeader_Output_Raw) XXX_Unmarshal(b []byte) error

type ModelConfig 

type ModelConfig struct {
	//@@  .. cpp:var:: string name
	//@@
	//@@     The name of the model.
	//@@
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	//@@  .. cpp:var:: string platform
	//@@
	//@@     The framework for the model. Possible values are
	//@@     "tensorrt_plan", "tensorflow_graphdef",
	//@@     "tensorflow_savedmodel", and "caffe2_netdef".
	//@@
	Platform string `protobuf:"bytes,2,opt,name=platform,proto3" json:"platform,omitempty"`
	//@@  .. cpp:var:: ModelVersionPolicy version_policy
	//@@
	//@@     Policy indicating which version(s) of the model will be served.
	//@@
	VersionPolicy *ModelVersionPolicy `protobuf:"bytes,3,opt,name=version_policy,json=versionPolicy,proto3" json:"version_policy,omitempty"`
	//@@  .. cpp:var:: int32 max_batch_size
	//@@
	//@@     Maximum batch size allowed for inference. This can only decrease
	//@@     what is allowed by the model itself. A max_batch_size value of 0
	//@@     indicates that batching is not allowed for the model and the
	//@@     dimension/shape of the input and output tensors must exactly
	//@@     match what is specified in the input and output configuration. A
	//@@     max_batch_size value > 0 indicates that batching is allowed and
	//@@     so the model expects the input tensors to have an additional
	//@@     initial dimension for the batching that is not specified in the
	//@@     input (for example, if the model supports batched inputs of
	//@@     2-dimensional tensors then the model configuration will specify
	//@@     the input shape as [ X, Y ] but the model will expect the actual
	//@@     input tensors to have shape [ N, X, Y ]). For max_batch_size > 0
	//@@     returned outputs will also have an additional initial dimension
	//@@     for the batch.
	//@@
	MaxBatchSize int32 `protobuf:"varint,4,opt,name=max_batch_size,json=maxBatchSize,proto3" json:"max_batch_size,omitempty"`
	//@@  .. cpp:var:: ModelInput input (repeated)
	//@@
	//@@     The inputs request by the model.
	//@@
	Input []*ModelInput `protobuf:"bytes,5,rep,name=input,proto3" json:"input,omitempty"`
	//@@  .. cpp:var:: ModelOutput output (repeated)
	//@@
	//@@     The outputs produced by the model.
	//@@
	Output []*ModelOutput `protobuf:"bytes,6,rep,name=output,proto3" json:"output,omitempty"`
	//@@  .. cpp:var:: ModelOptimizationPolicy optimization
	//@@
	//@@     Optimization configuration for the model. If not specified
	//@@     then default optimization policy is used.
	//@@
	Optimization *ModelOptimizationPolicy `protobuf:"bytes,12,opt,name=optimization,proto3" json:"optimization,omitempty"`
	//@@  .. cpp:var:: oneof scheduling_choice
	//@@
	//@@     The scheduling policy for the model. If not specified the
	//@@     default scheduling policy is used for the model. The default
	//@@     policy is to execute each inference request independently.
	//@@
	//
	// Types that are valid to be assigned to SchedulingChoice:
	//	*ModelConfig_DynamicBatching
	//	*ModelConfig_SequenceBatching
	//	*ModelConfig_EnsembleScheduling
	SchedulingChoice isModelConfig_SchedulingChoice `protobuf_oneof:"scheduling_choice"`
	//@@  .. cpp:var:: ModelInstanceGroup instance_group (repeated)
	//@@
	//@@     Instances of this model. If not specified, one instance
	//@@     of the model will be instantiated on each available GPU.
	//@@
	InstanceGroup []*ModelInstanceGroup `protobuf:"bytes,7,rep,name=instance_group,json=instanceGroup,proto3" json:"instance_group,omitempty"`
	//@@  .. cpp:var:: string default_model_filename
	//@@
	//@@     Optional filename of the model file to use if a
	//@@     compute-capability specific model is not specified in
	//@@     :cpp:var:`cc_model_names`. If not specified the default name
	//@@     is 'model.graphdef', 'model.savedmodel', 'model.plan' or
	//@@     'model.netdef' depending on the model type.
	//@@
	DefaultModelFilename string `protobuf:"bytes,8,opt,name=default_model_filename,json=defaultModelFilename,proto3" json:"default_model_filename,omitempty"`
	//@@  .. cpp:var:: map<string,string> cc_model_filenames
	//@@
	//@@     Optional map from CUDA compute capability to the filename of
	//@@     the model that supports that compute capability. The filename
	//@@     refers to a file within the model version directory.
	//@@
	CcModelFilenames map[string]string `` /* 199-byte string literal not displayed */
	//@@  .. cpp:var:: map<string,string> metric_tags
	//@@
	//@@     Optional metric tags. User-specific key-value pairs for metrics
	//@@     reported for this model. These tags are applied to the metrics
	//@@     reported on the HTTP metrics port.
	//@@
	MetricTags map[string]string `` /* 180-byte string literal not displayed */
	//@@  .. cpp:var:: map<string,ModelParameter> parameters
	//@@
	//@@     Optional model parameters. User-specified parameter values that
	//@@     are made available to custom backends.
	//@@
	Parameters           map[string]*ModelParameter `` /* 162-byte string literal not displayed */
	XXX_NoUnkeyedLiteral struct{}                   `json:"-"`
	XXX_unrecognized     []byte                     `json:"-"`
	XXX_sizecache        int32                      `json:"-"`
}

@@ @@.. cpp:var:: message ModelConfig @@ @@ A model configuration. @@

func (*ModelConfig) Descriptor 

func (*ModelConfig) Descriptor() ([]byte, []int)

func (*ModelConfig) GetCcModelFilenames 

func (m *ModelConfig) GetCcModelFilenames() map[string]string

func (*ModelConfig) GetDefaultModelFilename 

func (m *ModelConfig) GetDefaultModelFilename() string

func (*ModelConfig) GetDynamicBatching 

func (m *ModelConfig) GetDynamicBatching() *ModelDynamicBatching

func (*ModelConfig) GetEnsembleScheduling 

func (m *ModelConfig) GetEnsembleScheduling() *ModelEnsembling

func (*ModelConfig) GetInput 

func (m *ModelConfig) GetInput() []*ModelInput

func (*ModelConfig) GetInstanceGroup 

func (m *ModelConfig) GetInstanceGroup() []*ModelInstanceGroup

func (*ModelConfig) GetMaxBatchSize 

func (m *ModelConfig) GetMaxBatchSize() int32

func (*ModelConfig) GetMetricTags 

func (m *ModelConfig) GetMetricTags() map[string]string

func (*ModelConfig) GetName 

func (m *ModelConfig) GetName() string

func (*ModelConfig) GetOptimization 

func (m *ModelConfig) GetOptimization() *ModelOptimizationPolicy

func (*ModelConfig) GetOutput 

func (m *ModelConfig) GetOutput() []*ModelOutput

func (*ModelConfig) GetParameters 

func (m *ModelConfig) GetParameters() map[string]*ModelParameter

func (*ModelConfig) GetPlatform 

func (m *ModelConfig) GetPlatform() string

func (*ModelConfig) GetSchedulingChoice 

func (m *ModelConfig) GetSchedulingChoice() isModelConfig_SchedulingChoice

func (*ModelConfig) GetSequenceBatching 

func (m *ModelConfig) GetSequenceBatching() *ModelSequenceBatching

func (*ModelConfig) GetVersionPolicy 

func (m *ModelConfig) GetVersionPolicy() *ModelVersionPolicy

func (*ModelConfig) ProtoMessage 

func (*ModelConfig) ProtoMessage()

func (*ModelConfig) Reset 

func (m *ModelConfig) Reset()

func (*ModelConfig) String 

func (m *ModelConfig) String() string

func (*ModelConfig) XXX_DiscardUnknown 

func (m *ModelConfig) XXX_DiscardUnknown()

func (*ModelConfig) XXX_Marshal 

func (m *ModelConfig) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelConfig) XXX_Merge 

func (m *ModelConfig) XXX_Merge(src proto.Message)

func (*ModelConfig) XXX_OneofWrappers 

func (*ModelConfig) XXX_OneofWrappers() []interface{}

XXX_OneofWrappers is for the internal use of the proto package.

func (*ModelConfig) XXX_Size 

func (m *ModelConfig) XXX_Size() int

func (*ModelConfig) XXX_Unmarshal 

func (m *ModelConfig) XXX_Unmarshal(b []byte) error

type ModelConfig_DynamicBatching 

type ModelConfig_DynamicBatching struct {
	DynamicBatching *ModelDynamicBatching `protobuf:"bytes,11,opt,name=dynamic_batching,json=dynamicBatching,proto3,oneof"`
}

type ModelConfig_EnsembleScheduling 

type ModelConfig_EnsembleScheduling struct {
	EnsembleScheduling *ModelEnsembling `protobuf:"bytes,15,opt,name=ensemble_scheduling,json=ensembleScheduling,proto3,oneof"`
}

type ModelConfig_SequenceBatching 

type ModelConfig_SequenceBatching struct {
	SequenceBatching *ModelSequenceBatching `protobuf:"bytes,13,opt,name=sequence_batching,json=sequenceBatching,proto3,oneof"`
}

type ModelDynamicBatching 

type ModelDynamicBatching struct {
	//@@  .. cpp:var:: int32 preferred_batch_size (repeated)
	//@@
	//@@     Preferred batch sizes for dynamic batching. If a batch of one of
	//@@     these sizes can be formed it will be executed immediately.  If
	//@@     not specified a preferred batch size will be chosen automatically
	//@@     based on model and GPU characteristics.
	//@@
	PreferredBatchSize []int32 `protobuf:"varint,1,rep,packed,name=preferred_batch_size,json=preferredBatchSize,proto3" json:"preferred_batch_size,omitempty"`
	//@@  .. cpp:var:: uint64 max_queue_delay_microseconds
	//@@
	//@@     The maximum time, in microseconds, a request will be delayed in
	//@@     the scheduling queue to wait for additional requests for
	//@@     batching. Default is 0.
	//@@
	MaxQueueDelayMicroseconds uint64   `` /* 141-byte string literal not displayed */
	XXX_NoUnkeyedLiteral      struct{} `json:"-"`
	XXX_unrecognized          []byte   `json:"-"`
	XXX_sizecache             int32    `json:"-"`
}

@@ @@.. cpp:var:: message ModelDynamicBatching @@ @@ Dynamic batching configuration. These settings control how dynamic @@ batching operates for the model. @@

func (*ModelDynamicBatching) Descriptor 

func (*ModelDynamicBatching) Descriptor() ([]byte, []int)

func (*ModelDynamicBatching) GetMaxQueueDelayMicroseconds 

func (m *ModelDynamicBatching) GetMaxQueueDelayMicroseconds() uint64

func (*ModelDynamicBatching) GetPreferredBatchSize 

func (m *ModelDynamicBatching) GetPreferredBatchSize() []int32

func (*ModelDynamicBatching) ProtoMessage 

func (*ModelDynamicBatching) ProtoMessage()

func (*ModelDynamicBatching) Reset 

func (m *ModelDynamicBatching) Reset()

func (*ModelDynamicBatching) String 

func (m *ModelDynamicBatching) String() string

func (*ModelDynamicBatching) XXX_DiscardUnknown 

func (m *ModelDynamicBatching) XXX_DiscardUnknown()

func (*ModelDynamicBatching) XXX_Marshal 

func (m *ModelDynamicBatching) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelDynamicBatching) XXX_Merge 

func (m *ModelDynamicBatching) XXX_Merge(src proto.Message)

func (*ModelDynamicBatching) XXX_Size 

func (m *ModelDynamicBatching) XXX_Size() int

func (*ModelDynamicBatching) XXX_Unmarshal 

func (m *ModelDynamicBatching) XXX_Unmarshal(b []byte) error

type ModelEnsembling 

type ModelEnsembling struct {
	//@@  .. cpp:var:: Step step (repeated)
	//@@
	//@@     The models and the input / output mappings used within the ensemble.
	//@@
	Step                 []*ModelEnsembling_Step `protobuf:"bytes,1,rep,name=step,proto3" json:"step,omitempty"`
	XXX_NoUnkeyedLiteral struct{}                `json:"-"`
	XXX_unrecognized     []byte                  `json:"-"`
	XXX_sizecache        int32                   `json:"-"`
}

@@ @@.. cpp:var:: message ModelEnsembling @@ @@ Model ensembling configuration. These settings specify the models that @@ compose the ensemble and how data flows between the models. @@

func (*ModelEnsembling) Descriptor 

func (*ModelEnsembling) Descriptor() ([]byte, []int)

func (*ModelEnsembling) GetStep 

func (m *ModelEnsembling) GetStep() []*ModelEnsembling_Step

func (*ModelEnsembling) ProtoMessage 

func (*ModelEnsembling) ProtoMessage()

func (*ModelEnsembling) Reset 

func (m *ModelEnsembling) Reset()

func (*ModelEnsembling) String 

func (m *ModelEnsembling) String() string

func (*ModelEnsembling) XXX_DiscardUnknown 

func (m *ModelEnsembling) XXX_DiscardUnknown()

func (*ModelEnsembling) XXX_Marshal 

func (m *ModelEnsembling) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelEnsembling) XXX_Merge 

func (m *ModelEnsembling) XXX_Merge(src proto.Message)

func (*ModelEnsembling) XXX_Size 

func (m *ModelEnsembling) XXX_Size() int

func (*ModelEnsembling) XXX_Unmarshal 

func (m *ModelEnsembling) XXX_Unmarshal(b []byte) error

type ModelEnsembling_Step 

type ModelEnsembling_Step struct {
	//@@  .. cpp:var:: string model_name
	//@@
	//@@     The name of the model to execute for this step of the ensemble.
	//@@
	ModelName string `protobuf:"bytes,1,opt,name=model_name,json=modelName,proto3" json:"model_name,omitempty"`
	//@@  .. cpp:var:: int64 model_version
	//@@
	//@@     The version of the model to use for inference. If -1
	//@@     the latest/most-recent version of the model is used.
	//@@
	ModelVersion int64 `protobuf:"varint,2,opt,name=model_version,json=modelVersion,proto3" json:"model_version,omitempty"`
	//@@  .. cpp:var:: map<string,string> input_map
	//@@
	//@@     Map from name of an input tensor on this step's model to ensemble
	//@@     tensor name. The ensemble tensor must have the same data type and
	//@@     shape as the model input. Each model input must be assigned to
	//@@     one ensemble tensor, but the same ensemble tensor can be assigned
	//@@     to multiple model inputs.
	//@@
	InputMap map[string]string `` /* 173-byte string literal not displayed */
	//@@  .. cpp:var:: map<string,string> output_map
	//@@
	//@@     Map from name of an output tensor on this step's model to ensemble
	//@@     tensor name. The data type and shape of the ensemble tensor will
	//@@     be inferred from the model output. It is optional to assign all
	//@@     model outputs to ensemble tensors. One ensemble tensor name
	//@@     can appear in an output map only once.
	//@@
	OutputMap            map[string]string `` /* 176-byte string literal not displayed */
	XXX_NoUnkeyedLiteral struct{}          `json:"-"`
	XXX_unrecognized     []byte            `json:"-"`
	XXX_sizecache        int32             `json:"-"`
}

@@ .. cpp:var:: message Step @@ @@ Each step specifies a model included in the ensemble, @@ maps ensemble tensor names to the model input tensors, @@ and maps model output tensors to ensemble tensor names @@

func (*ModelEnsembling_Step) Descriptor 

func (*ModelEnsembling_Step) Descriptor() ([]byte, []int)

func (*ModelEnsembling_Step) GetInputMap 

func (m *ModelEnsembling_Step) GetInputMap() map[string]string

func (*ModelEnsembling_Step) GetModelName 

func (m *ModelEnsembling_Step) GetModelName() string

func (*ModelEnsembling_Step) GetModelVersion 

func (m *ModelEnsembling_Step) GetModelVersion() int64

func (*ModelEnsembling_Step) GetOutputMap 

func (m *ModelEnsembling_Step) GetOutputMap() map[string]string

func (*ModelEnsembling_Step) ProtoMessage 

func (*ModelEnsembling_Step) ProtoMessage()

func (*ModelEnsembling_Step) Reset 

func (m *ModelEnsembling_Step) Reset()

func (*ModelEnsembling_Step) String 

func (m *ModelEnsembling_Step) String() string

func (*ModelEnsembling_Step) XXX_DiscardUnknown 

func (m *ModelEnsembling_Step) XXX_DiscardUnknown()

func (*ModelEnsembling_Step) XXX_Marshal 

func (m *ModelEnsembling_Step) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelEnsembling_Step) XXX_Merge 

func (m *ModelEnsembling_Step) XXX_Merge(src proto.Message)

func (*ModelEnsembling_Step) XXX_Size 

func (m *ModelEnsembling_Step) XXX_Size() int

func (*ModelEnsembling_Step) XXX_Unmarshal 

func (m *ModelEnsembling_Step) XXX_Unmarshal(b []byte) error

type ModelInput 

type ModelInput struct {
	//@@  .. cpp:var:: string name
	//@@
	//@@     The name of the input.
	//@@
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	//@@  .. cpp:var:: DataType data_type
	//@@
	//@@     The data-type of the input.
	//@@
	DataType DataType `protobuf:"varint,2,opt,name=data_type,json=dataType,proto3,enum=nvidia.inferenceserver.DataType" json:"data_type,omitempty"`
	//@@  .. cpp:var:: Format format
	//@@
	//@@     The format of the input. Optional.
	//@@
	Format ModelInput_Format `protobuf:"varint,3,opt,name=format,proto3,enum=nvidia.inferenceserver.ModelInput_Format" json:"format,omitempty"`
	//@@  .. cpp:var:: int64 dims (repeated)
	//@@
	//@@     The dimensions/shape of the input tensor that must be provided
	//@@     when invoking the inference API for this model.
	//@@
	Dims []int64 `protobuf:"varint,4,rep,packed,name=dims,proto3" json:"dims,omitempty"`
	//@@  .. cpp:var:: ModelTensorReshape reshape
	//@@
	//@@     The shape expected for this input by the backend. The input will
	//@@     be reshaped to this before being presented to the backend. The
	//@@     reshape must have the same number of elements as the input shape
	//@@     specified by 'dims'. Optional.
	//@@
	Reshape              *ModelTensorReshape `protobuf:"bytes,5,opt,name=reshape,proto3" json:"reshape,omitempty"`
	XXX_NoUnkeyedLiteral struct{}            `json:"-"`
	XXX_unrecognized     []byte              `json:"-"`
	XXX_sizecache        int32               `json:"-"`
}

@@ @@.. cpp:var:: message ModelInput @@ @@ An input required by the model. @@

func (*ModelInput) Descriptor 

func (*ModelInput) Descriptor() ([]byte, []int)

func (*ModelInput) GetDataType 

func (m *ModelInput) GetDataType() DataType

func (*ModelInput) GetDims 

func (m *ModelInput) GetDims() []int64

func (*ModelInput) GetFormat 

func (m *ModelInput) GetFormat() ModelInput_Format

func (*ModelInput) GetName 

func (m *ModelInput) GetName() string

func (*ModelInput) GetReshape 

func (m *ModelInput) GetReshape() *ModelTensorReshape

func (*ModelInput) ProtoMessage 

func (*ModelInput) ProtoMessage()

func (*ModelInput) Reset 

func (m *ModelInput) Reset()

func (*ModelInput) String 

func (m *ModelInput) String() string

func (*ModelInput) XXX_DiscardUnknown 

func (m *ModelInput) XXX_DiscardUnknown()

func (*ModelInput) XXX_Marshal 

func (m *ModelInput) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelInput) XXX_Merge 

func (m *ModelInput) XXX_Merge(src proto.Message)

func (*ModelInput) XXX_Size 

func (m *ModelInput) XXX_Size() int

func (*ModelInput) XXX_Unmarshal 

func (m *ModelInput) XXX_Unmarshal(b []byte) error

type ModelInput_Format 

type ModelInput_Format int32

@@ @@ .. cpp:enum:: Format @@ @@ The format for the input. @@ 

const (
	//@@    .. cpp:enumerator:: Format::FORMAT_NONE = 0
	//@@
	//@@       The input has no specific format. This is the default.
	//@@
	ModelInput_FORMAT_NONE ModelInput_Format = 0
	//@@    .. cpp:enumerator:: Format::FORMAT_NHWC = 1
	//@@
	//@@       HWC image format. Tensors with this format require 3 dimensions
	//@@       if the model does not support batching (max_batch_size = 0) or 4
	//@@       dimensions if the model does support batching (max_batch_size
	//@@       >= 1). In either case the 'dims' below should only specify the
	//@@       3 non-batch dimensions (i.e. HWC or CHW).
	//@@
	ModelInput_FORMAT_NHWC ModelInput_Format = 1
	//@@    .. cpp:enumerator:: Format::FORMAT_NCHW = 2
	//@@
	//@@       CHW image format. Tensors with this format require 3 dimensions
	//@@       if the model does not support batching (max_batch_size = 0) or 4
	//@@       dimensions if the model does support batching (max_batch_size
	//@@       >= 1). In either case the 'dims' below should only specify the
	//@@       3 non-batch dimensions (i.e. HWC or CHW).
	//@@
	ModelInput_FORMAT_NCHW ModelInput_Format = 2
)

func (ModelInput_Format) EnumDescriptor 

func (ModelInput_Format) EnumDescriptor() ([]byte, []int)

func (ModelInput_Format) String 

func (x ModelInput_Format) String() string

type ModelInstanceGroup 

type ModelInstanceGroup struct {
	//@@  .. cpp:var:: string name
	//@@
	//@@     Optional name of this group of instances. If not specified the
	//@@     name will be formed as <model name>_<group number>. The name of
	//@@     individual instances will be further formed by a unique instance
	//@@     number and GPU index:
	//@@
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	//@@  .. cpp:var:: Kind kind
	//@@
	//@@     The kind of this instance group. Default is KIND_AUTO. If
	//@@     KIND_AUTO or KIND_GPU then both 'count' and 'gpu' are valid and
	//@@     may be specified. If KIND_CPU only 'count' is valid and 'gpu'
	//@@     cannot be specified.
	//@@
	Kind ModelInstanceGroup_Kind `protobuf:"varint,4,opt,name=kind,proto3,enum=nvidia.inferenceserver.ModelInstanceGroup_Kind" json:"kind,omitempty"`
	//@@  .. cpp:var:: int32 count
	//@@
	//@@     For a group assigned to GPU, the number of instances created for
	//@@     each GPU listed in 'gpus'. For a group assigned to CPU the number
	//@@     of instances created. Default is 1.
	Count int32 `protobuf:"varint,2,opt,name=count,proto3" json:"count,omitempty"`
	//@@  .. cpp:var:: int32 gpus (repeated)
	//@@
	//@@     GPU(s) where instances should be available. For each GPU listed,
	//@@     'count' instances of the model will be available. Setting 'gpus'
	//@@     to empty (or not specifying at all) is eqivalent to listing all
	//@@     available GPUs.
	//@@
	Gpus                 []int32  `protobuf:"varint,3,rep,packed,name=gpus,proto3" json:"gpus,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@.. cpp:var:: message ModelInstanceGroup @@ @@ A group of one or more instances of a model and resources made @@ available for those instances. @@

func (*ModelInstanceGroup) Descriptor 

func (*ModelInstanceGroup) Descriptor() ([]byte, []int)

func (*ModelInstanceGroup) GetCount 

func (m *ModelInstanceGroup) GetCount() int32

func (*ModelInstanceGroup) GetGpus 

func (m *ModelInstanceGroup) GetGpus() []int32

func (*ModelInstanceGroup) GetKind 

func (m *ModelInstanceGroup) GetKind() ModelInstanceGroup_Kind

func (*ModelInstanceGroup) GetName 

func (m *ModelInstanceGroup) GetName() string

func (*ModelInstanceGroup) ProtoMessage 

func (*ModelInstanceGroup) ProtoMessage()

func (*ModelInstanceGroup) Reset 

func (m *ModelInstanceGroup) Reset()

func (*ModelInstanceGroup) String 

func (m *ModelInstanceGroup) String() string

func (*ModelInstanceGroup) XXX_DiscardUnknown 

func (m *ModelInstanceGroup) XXX_DiscardUnknown()

func (*ModelInstanceGroup) XXX_Marshal 

func (m *ModelInstanceGroup) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelInstanceGroup) XXX_Merge 

func (m *ModelInstanceGroup) XXX_Merge(src proto.Message)

func (*ModelInstanceGroup) XXX_Size 

func (m *ModelInstanceGroup) XXX_Size() int

func (*ModelInstanceGroup) XXX_Unmarshal 

func (m *ModelInstanceGroup) XXX_Unmarshal(b []byte) error

type ModelInstanceGroup_Kind 

type ModelInstanceGroup_Kind int32

@@ @@ .. cpp:enum:: Kind @@ @@ Kind of this instance group. @@ 

const (
	//@@    .. cpp:enumerator:: Kind::KIND_AUTO = 0
	//@@
	//@@       This instance group represents instances that can run on either
	//@@       CPU or GPU. If all GPUs listed in 'gpus' are available then
	//@@       instances will be created on GPU(s), otherwise instances will
	//@@       be created on CPU.
	//@@
	ModelInstanceGroup_KIND_AUTO ModelInstanceGroup_Kind = 0
	//@@    .. cpp:enumerator:: Kind::KIND_GPU = 1
	//@@
	//@@       This instance group represents instances that must run on the
	//@@       GPU.
	//@@
	ModelInstanceGroup_KIND_GPU ModelInstanceGroup_Kind = 1
	//@@    .. cpp:enumerator:: Kind::KIND_CPU = 2
	//@@
	//@@       This instance group represents instances that must run on the
	//@@       CPU.
	//@@
	ModelInstanceGroup_KIND_CPU ModelInstanceGroup_Kind = 2
)

func (ModelInstanceGroup_Kind) EnumDescriptor 

func (ModelInstanceGroup_Kind) EnumDescriptor() ([]byte, []int)

func (ModelInstanceGroup_Kind) String 

func (x ModelInstanceGroup_Kind) String() string

type ModelOptimizationPolicy 

type ModelOptimizationPolicy struct {
	//@@  .. cpp:var:: Graph graph
	//@@
	//@@     The graph optimization setting for the model. Optional.
	//@@
	Graph *ModelOptimizationPolicy_Graph `protobuf:"bytes,1,opt,name=graph,proto3" json:"graph,omitempty"`
	//@@  .. cpp:var:: ModelPriority priority
	//@@
	//@@     The priority setting for the model. Optional.
	//@@
	Priority ModelOptimizationPolicy_ModelPriority `` /* 136-byte string literal not displayed */
	//@@  .. cpp:var:: Cuda cuda
	//@@
	//@@     CUDA-specific optimization settings. Optional.
	//@@
	Cuda                 *ModelOptimizationPolicy_Cuda `protobuf:"bytes,3,opt,name=cuda,proto3" json:"cuda,omitempty"`
	XXX_NoUnkeyedLiteral struct{}                      `json:"-"`
	XXX_unrecognized     []byte                        `json:"-"`
	XXX_sizecache        int32                         `json:"-"`
}

@@ @@.. cpp:var:: message ModelOptimizationPolicy @@ @@ Optimization settings for a model. These settings control if/how a @@ model is optimized and prioritized by the backend framework when @@ it is loaded. @@

func (*ModelOptimizationPolicy) Descriptor 

func (*ModelOptimizationPolicy) Descriptor() ([]byte, []int)

func (*ModelOptimizationPolicy) GetCuda 

func (m *ModelOptimizationPolicy) GetCuda() *ModelOptimizationPolicy_Cuda

func (*ModelOptimizationPolicy) GetGraph 

func (m *ModelOptimizationPolicy) GetGraph() *ModelOptimizationPolicy_Graph

func (*ModelOptimizationPolicy) GetPriority 

func (m *ModelOptimizationPolicy) GetPriority() ModelOptimizationPolicy_ModelPriority

func (*ModelOptimizationPolicy) ProtoMessage 

func (*ModelOptimizationPolicy) ProtoMessage()

func (*ModelOptimizationPolicy) Reset 

func (m *ModelOptimizationPolicy) Reset()

func (*ModelOptimizationPolicy) String 

func (m *ModelOptimizationPolicy) String() string

func (*ModelOptimizationPolicy) XXX_DiscardUnknown 

func (m *ModelOptimizationPolicy) XXX_DiscardUnknown()

func (*ModelOptimizationPolicy) XXX_Marshal 

func (m *ModelOptimizationPolicy) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelOptimizationPolicy) XXX_Merge 

func (m *ModelOptimizationPolicy) XXX_Merge(src proto.Message)

func (*ModelOptimizationPolicy) XXX_Size 

func (m *ModelOptimizationPolicy) XXX_Size() int

func (*ModelOptimizationPolicy) XXX_Unmarshal 

func (m *ModelOptimizationPolicy) XXX_Unmarshal(b []byte) error

type ModelOptimizationPolicy_Cuda 

type ModelOptimizationPolicy_Cuda struct {
	//@@    .. cpp:var:: bool graphs
	//@@
	//@@       Use CUDA graphs API to capture model operations and execute
	//@@       them more efficiently. Currently only recognized by TensorRT
	//@@       backend.
	//@@
	Graphs               bool     `protobuf:"varint,1,opt,name=graphs,proto3" json:"graphs,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@ .. cpp:var:: message Cuda @@ @@ CUDA-specific optimization settings. @@

func (*ModelOptimizationPolicy_Cuda) Descriptor 

func (*ModelOptimizationPolicy_Cuda) Descriptor() ([]byte, []int)

func (*ModelOptimizationPolicy_Cuda) GetGraphs 

func (m *ModelOptimizationPolicy_Cuda) GetGraphs() bool

func (*ModelOptimizationPolicy_Cuda) ProtoMessage 

func (*ModelOptimizationPolicy_Cuda) ProtoMessage()

func (*ModelOptimizationPolicy_Cuda) Reset 

func (m *ModelOptimizationPolicy_Cuda) Reset()

func (*ModelOptimizationPolicy_Cuda) String 

func (m *ModelOptimizationPolicy_Cuda) String() string

func (*ModelOptimizationPolicy_Cuda) XXX_DiscardUnknown 

func (m *ModelOptimizationPolicy_Cuda) XXX_DiscardUnknown()

func (*ModelOptimizationPolicy_Cuda) XXX_Marshal 

func (m *ModelOptimizationPolicy_Cuda) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelOptimizationPolicy_Cuda) XXX_Merge 

func (m *ModelOptimizationPolicy_Cuda) XXX_Merge(src proto.Message)

func (*ModelOptimizationPolicy_Cuda) XXX_Size 

func (m *ModelOptimizationPolicy_Cuda) XXX_Size() int

func (*ModelOptimizationPolicy_Cuda) XXX_Unmarshal 

func (m *ModelOptimizationPolicy_Cuda) XXX_Unmarshal(b []byte) error

type ModelOptimizationPolicy_Graph 

type ModelOptimizationPolicy_Graph struct {
	//@@    .. cpp:var:: int32 level
	//@@
	//@@       The optimization level. Defaults to 0 (zero) if not specified.
	//@@
	//@@         - -1: Disabled
	//@@         -  0: Framework default
	//@@         -  1+: Enable optimization level (greater values indicate
	//@@            higher optimization levels)
	//@@
	Level                int32    `protobuf:"varint,1,opt,name=level,proto3" json:"level,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@ .. cpp:var:: message Graph @@ @@ Enable generic graph optimization of the model. If not specified @@ the framework's default level of optimization is used. Currently @@ only supported for TensorFlow graphdef and savedmodel models and @@ causes XLA to be enabled/disabled for the model. @@

func (*ModelOptimizationPolicy_Graph) Descriptor 

func (*ModelOptimizationPolicy_Graph) Descriptor() ([]byte, []int)

func (*ModelOptimizationPolicy_Graph) GetLevel 

func (m *ModelOptimizationPolicy_Graph) GetLevel() int32

func (*ModelOptimizationPolicy_Graph) ProtoMessage 

func (*ModelOptimizationPolicy_Graph) ProtoMessage()

func (*ModelOptimizationPolicy_Graph) Reset 

func (m *ModelOptimizationPolicy_Graph) Reset()

func (*ModelOptimizationPolicy_Graph) String 

func (m *ModelOptimizationPolicy_Graph) String() string

func (*ModelOptimizationPolicy_Graph) XXX_DiscardUnknown 

func (m *ModelOptimizationPolicy_Graph) XXX_DiscardUnknown()

func (*ModelOptimizationPolicy_Graph) XXX_Marshal 

func (m *ModelOptimizationPolicy_Graph) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelOptimizationPolicy_Graph) XXX_Merge 

func (m *ModelOptimizationPolicy_Graph) XXX_Merge(src proto.Message)

func (*ModelOptimizationPolicy_Graph) XXX_Size 

func (m *ModelOptimizationPolicy_Graph) XXX_Size() int

func (*ModelOptimizationPolicy_Graph) XXX_Unmarshal 

func (m *ModelOptimizationPolicy_Graph) XXX_Unmarshal(b []byte) error

type ModelOptimizationPolicy_ModelPriority 

type ModelOptimizationPolicy_ModelPriority int32

@@ @@ .. cpp:enum:: ModelPriority @@ @@ Model priorities. A model will be given scheduling and execution @@ preference over models at lower priorities. Current model @@ priorities only work for TensorRT models. @@ 

const (
	//@@    .. cpp:enumerator:: ModelPriority::PRIORITY_DEFAULT = 0
	//@@
	//@@       The default model priority.
	//@@
	ModelOptimizationPolicy_PRIORITY_DEFAULT ModelOptimizationPolicy_ModelPriority = 0
	//@@    .. cpp:enumerator:: ModelPriority::PRIORITY_MAX = 1
	//@@
	//@@       The maximum model priority.
	//@@
	ModelOptimizationPolicy_PRIORITY_MAX ModelOptimizationPolicy_ModelPriority = 1
	//@@    .. cpp:enumerator:: ModelPriority::PRIORITY_MIN = 2
	//@@
	//@@       The minimum model priority.
	//@@
	ModelOptimizationPolicy_PRIORITY_MIN ModelOptimizationPolicy_ModelPriority = 2
)

func (ModelOptimizationPolicy_ModelPriority) EnumDescriptor 

func (ModelOptimizationPolicy_ModelPriority) EnumDescriptor() ([]byte, []int)

func (ModelOptimizationPolicy_ModelPriority) String 

func (x ModelOptimizationPolicy_ModelPriority) String() string

type ModelOutput 

type ModelOutput struct {
	//@@  .. cpp:var:: string name
	//@@
	//@@     The name of the output.
	//@@
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	//@@  .. cpp:var:: DataType data_type
	//@@
	//@@     The data-type of the output.
	//@@
	DataType DataType `protobuf:"varint,2,opt,name=data_type,json=dataType,proto3,enum=nvidia.inferenceserver.DataType" json:"data_type,omitempty"`
	//@@  .. cpp:var:: int64 dims (repeated)
	//@@
	//@@     The dimensions/shape of the output tensor.
	//@@
	Dims []int64 `protobuf:"varint,3,rep,packed,name=dims,proto3" json:"dims,omitempty"`
	//@@  .. cpp:var:: ModelTensorReshape reshape
	//@@
	//@@     The shape produced for this output by the backend. The output will
	//@@     be reshaped from this to the shape specifed in 'dims' before being
	//@@     returned in the inference response. The reshape must have the same
	//@@     number of elements as the output shape specified by 'dims'. Optional.
	//@@
	Reshape *ModelTensorReshape `protobuf:"bytes,5,opt,name=reshape,proto3" json:"reshape,omitempty"`
	//@@  .. cpp:var:: string label_filename
	//@@
	//@@     The label file associated with this output. Should be specified only
	//@@     for outputs that represent classifications. Optional.
	//@@
	LabelFilename        string   `protobuf:"bytes,4,opt,name=label_filename,json=labelFilename,proto3" json:"label_filename,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@.. cpp:var:: message ModelOutput @@ @@ An output produced by the model. @@

func (*ModelOutput) Descriptor 

func (*ModelOutput) Descriptor() ([]byte, []int)

func (*ModelOutput) GetDataType 

func (m *ModelOutput) GetDataType() DataType

func (*ModelOutput) GetDims 

func (m *ModelOutput) GetDims() []int64

func (*ModelOutput) GetLabelFilename 

func (m *ModelOutput) GetLabelFilename() string

func (*ModelOutput) GetName 

func (m *ModelOutput) GetName() string

func (*ModelOutput) GetReshape 

func (m *ModelOutput) GetReshape() *ModelTensorReshape

func (*ModelOutput) ProtoMessage 

func (*ModelOutput) ProtoMessage()

func (*ModelOutput) Reset 

func (m *ModelOutput) Reset()

func (*ModelOutput) String 

func (m *ModelOutput) String() string

func (*ModelOutput) XXX_DiscardUnknown 

func (m *ModelOutput) XXX_DiscardUnknown()

func (*ModelOutput) XXX_Marshal 

func (m *ModelOutput) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelOutput) XXX_Merge 

func (m *ModelOutput) XXX_Merge(src proto.Message)

func (*ModelOutput) XXX_Size 

func (m *ModelOutput) XXX_Size() int

func (*ModelOutput) XXX_Unmarshal 

func (m *ModelOutput) XXX_Unmarshal(b []byte) error

type ModelParameter 

type ModelParameter struct {
	//@@  .. cpp:var:: string string_value
	//@@
	//@@     The string value of the parameter.
	//@@
	StringValue          string   `protobuf:"bytes,1,opt,name=string_value,json=stringValue,proto3" json:"string_value,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@.. cpp:var:: message ModelParameter @@ @@ A model parameter. @@

func (*ModelParameter) Descriptor 

func (*ModelParameter) Descriptor() ([]byte, []int)

func (*ModelParameter) GetStringValue 

func (m *ModelParameter) GetStringValue() string

func (*ModelParameter) ProtoMessage 

func (*ModelParameter) ProtoMessage()

func (*ModelParameter) Reset 

func (m *ModelParameter) Reset()

func (*ModelParameter) String 

func (m *ModelParameter) String() string

func (*ModelParameter) XXX_DiscardUnknown 

func (m *ModelParameter) XXX_DiscardUnknown()

func (*ModelParameter) XXX_Marshal 

func (m *ModelParameter) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelParameter) XXX_Merge 

func (m *ModelParameter) XXX_Merge(src proto.Message)

func (*ModelParameter) XXX_Size 

func (m *ModelParameter) XXX_Size() int

func (*ModelParameter) XXX_Unmarshal 

func (m *ModelParameter) XXX_Unmarshal(b []byte) error

type ModelReadyState 

type ModelReadyState int32

@@ @@.. cpp:enum:: ModelReadyState @@ @@ Readiness status for models. @@ 

const (
	//@@  .. cpp:enumerator:: ModelReadyState::MODEL_UNKNOWN = 0
	//@@
	//@@     The model is in an unknown state. The model is not available for
	//@@     inferencing.
	//@@
	ModelReadyState_MODEL_UNKNOWN ModelReadyState = 0
	//@@  .. cpp:enumerator:: ModelReadyState::MODEL_READY = 1
	//@@
	//@@     The model is ready and available for inferencing.
	//@@
	ModelReadyState_MODEL_READY ModelReadyState = 1
	//@@  .. cpp:enumerator:: ModelReadyState::MODEL_UNAVAILABLE = 2
	//@@
	//@@     The model is unavailable, indicating that the model failed to
	//@@     load or has been implicitly or explicitly unloaded. The model is
	//@@     not available for inferencing.
	//@@
	ModelReadyState_MODEL_UNAVAILABLE ModelReadyState = 2
	//@@  .. cpp:enumerator:: ModelReadyState::MODEL_LOADING = 3
	//@@
	//@@     The model is being loaded by the inference server. The model is
	//@@     not available for inferencing.
	//@@
	ModelReadyState_MODEL_LOADING ModelReadyState = 3
	//@@  .. cpp:enumerator:: ModelReadyState::MODEL_UNLOADING = 4
	//@@
	//@@     The model is being unloaded by the inference server. The model is
	//@@     not available for inferencing.
	//@@
	ModelReadyState_MODEL_UNLOADING ModelReadyState = 4
)

func (ModelReadyState) EnumDescriptor 

func (ModelReadyState) EnumDescriptor() ([]byte, []int)

func (ModelReadyState) String 

func (x ModelReadyState) String() string

type ModelSequenceBatching 

type ModelSequenceBatching struct {
	//@@  .. cpp:var:: uint64 max_sequence_idle_microseconds
	//@@
	//@@     The maximum time, in microseconds, that a sequence is allowed to
	//@@     be idle before it is aborted. The inference server considers a
	//@@     sequence idle when it does not have any inference request queued
	//@@     for the sequence. If this limit is exceeded, the inference server
	//@@     will free the batch slot allocated by the sequence and make it
	//@@     available for another sequence. If not specified (or specified as
	//@@     zero) a default value of 1000000 (1 second) is used.
	//@@
	MaxSequenceIdleMicroseconds uint64 `` /* 147-byte string literal not displayed */
	//@@  .. cpp:var:: ControlInput control_input (repeated)
	//@@
	//@@     The model input(s) that the server should use to communicate
	//@@     sequence start, stop, ready and similar control values to the
	//@@     model.
	//@@
	ControlInput         []*ModelSequenceBatching_ControlInput `protobuf:"bytes,2,rep,name=control_input,json=controlInput,proto3" json:"control_input,omitempty"`
	XXX_NoUnkeyedLiteral struct{}                              `json:"-"`
	XXX_unrecognized     []byte                                `json:"-"`
	XXX_sizecache        int32                                 `json:"-"`
}

@@ @@.. cpp:var:: message ModelSequenceBatching @@ @@ Sequence batching configuration. These settings control how sequence @@ batching operates for the model. @@

func (*ModelSequenceBatching) Descriptor 

func (*ModelSequenceBatching) Descriptor() ([]byte, []int)

func (*ModelSequenceBatching) GetControlInput 

func (m *ModelSequenceBatching) GetControlInput() []*ModelSequenceBatching_ControlInput

func (*ModelSequenceBatching) GetMaxSequenceIdleMicroseconds 

func (m *ModelSequenceBatching) GetMaxSequenceIdleMicroseconds() uint64

func (*ModelSequenceBatching) ProtoMessage 

func (*ModelSequenceBatching) ProtoMessage()

func (*ModelSequenceBatching) Reset 

func (m *ModelSequenceBatching) Reset()

func (*ModelSequenceBatching) String 

func (m *ModelSequenceBatching) String() string

func (*ModelSequenceBatching) XXX_DiscardUnknown 

func (m *ModelSequenceBatching) XXX_DiscardUnknown()

func (*ModelSequenceBatching) XXX_Marshal 

func (m *ModelSequenceBatching) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelSequenceBatching) XXX_Merge 

func (m *ModelSequenceBatching) XXX_Merge(src proto.Message)

func (*ModelSequenceBatching) XXX_Size 

func (m *ModelSequenceBatching) XXX_Size() int

func (*ModelSequenceBatching) XXX_Unmarshal 

func (m *ModelSequenceBatching) XXX_Unmarshal(b []byte) error

type ModelSequenceBatching_Control 

type ModelSequenceBatching_Control struct {
	//@@    .. cpp:var:: Kind kind
	//@@
	//@@       The kind of this control.
	//@@
	Kind ModelSequenceBatching_Control_Kind `protobuf:"varint,1,opt,name=kind,proto3,enum=nvidia.inferenceserver.ModelSequenceBatching_Control_Kind" json:"kind,omitempty"`
	//@@    .. cpp:var:: int32 int32_false_true (repeated)
	//@@
	//@@       The control's true and false setting is indicated by setting
	//@@       a value in an int32 tensor. The tensor must be a
	//@@       1-dimensional tensor with size equal to the batch size of
	//@@       the request. 'int32_false_true' must have two entries: the
	//@@       first the false value and the second the true value.
	//@@
	Int32FalseTrue []int32 `protobuf:"varint,2,rep,packed,name=int32_false_true,json=int32FalseTrue,proto3" json:"int32_false_true,omitempty"`
	//@@    .. cpp:var:: float fp32_false_true (repeated)
	//@@
	//@@       The control's true and false setting is indicated by setting
	//@@       a value in a fp32 tensor. The tensor must be a
	//@@       1-dimensional tensor with size equal to the batch size of
	//@@       the request. 'fp32_false_true' must have two entries: the
	//@@       first the false value and the second the true value.
	//@@
	Fp32FalseTrue        []float32 `protobuf:"fixed32,3,rep,packed,name=fp32_false_true,json=fp32FalseTrue,proto3" json:"fp32_false_true,omitempty"`
	XXX_NoUnkeyedLiteral struct{}  `json:"-"`
	XXX_unrecognized     []byte    `json:"-"`
	XXX_sizecache        int32     `json:"-"`
}

@@ .. cpp:var:: message Control @@ @@ A control is a binary signal to a backend. @@

func (*ModelSequenceBatching_Control) Descriptor 

func (*ModelSequenceBatching_Control) Descriptor() ([]byte, []int)

func (*ModelSequenceBatching_Control) GetFp32FalseTrue 

func (m *ModelSequenceBatching_Control) GetFp32FalseTrue() []float32

func (*ModelSequenceBatching_Control) GetInt32FalseTrue 

func (m *ModelSequenceBatching_Control) GetInt32FalseTrue() []int32

func (*ModelSequenceBatching_Control) GetKind 

func (m *ModelSequenceBatching_Control) GetKind() ModelSequenceBatching_Control_Kind

func (*ModelSequenceBatching_Control) ProtoMessage 

func (*ModelSequenceBatching_Control) ProtoMessage()

func (*ModelSequenceBatching_Control) Reset 

func (m *ModelSequenceBatching_Control) Reset()

func (*ModelSequenceBatching_Control) String 

func (m *ModelSequenceBatching_Control) String() string

func (*ModelSequenceBatching_Control) XXX_DiscardUnknown 

func (m *ModelSequenceBatching_Control) XXX_DiscardUnknown()

func (*ModelSequenceBatching_Control) XXX_Marshal 

func (m *ModelSequenceBatching_Control) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelSequenceBatching_Control) XXX_Merge 

func (m *ModelSequenceBatching_Control) XXX_Merge(src proto.Message)

func (*ModelSequenceBatching_Control) XXX_Size 

func (m *ModelSequenceBatching_Control) XXX_Size() int

func (*ModelSequenceBatching_Control) XXX_Unmarshal 

func (m *ModelSequenceBatching_Control) XXX_Unmarshal(b []byte) error

type ModelSequenceBatching_ControlInput 

type ModelSequenceBatching_ControlInput struct {
	//@@    .. cpp:var:: string name
	//@@
	//@@       The name of the model input.
	//@@
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	//@@    .. cpp:var:: Control control (repeated)
	//@@
	//@@       The control value(s) that should be communicated to the
	//@@       model using this model input.
	//@@
	Control              []*ModelSequenceBatching_Control `protobuf:"bytes,2,rep,name=control,proto3" json:"control,omitempty"`
	XXX_NoUnkeyedLiteral struct{}                         `json:"-"`
	XXX_unrecognized     []byte                           `json:"-"`
	XXX_sizecache        int32                            `json:"-"`
}

@@ .. cpp:var:: message ControlInput @@ @@ The sequence control values to communicate by a model input. @@

func (*ModelSequenceBatching_ControlInput) Descriptor 

func (*ModelSequenceBatching_ControlInput) Descriptor() ([]byte, []int)

func (*ModelSequenceBatching_ControlInput) GetControl 

func (m *ModelSequenceBatching_ControlInput) GetControl() []*ModelSequenceBatching_Control

func (*ModelSequenceBatching_ControlInput) GetName 

func (m *ModelSequenceBatching_ControlInput) GetName() string

func (*ModelSequenceBatching_ControlInput) ProtoMessage 

func (*ModelSequenceBatching_ControlInput) ProtoMessage()

func (*ModelSequenceBatching_ControlInput) Reset 

func (m *ModelSequenceBatching_ControlInput) Reset()

func (*ModelSequenceBatching_ControlInput) String 

func (m *ModelSequenceBatching_ControlInput) String() string

func (*ModelSequenceBatching_ControlInput) XXX_DiscardUnknown 

func (m *ModelSequenceBatching_ControlInput) XXX_DiscardUnknown()

func (*ModelSequenceBatching_ControlInput) XXX_Marshal 

func (m *ModelSequenceBatching_ControlInput) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelSequenceBatching_ControlInput) XXX_Merge 

func (m *ModelSequenceBatching_ControlInput) XXX_Merge(src proto.Message)

func (*ModelSequenceBatching_ControlInput) XXX_Size 

func (m *ModelSequenceBatching_ControlInput) XXX_Size() int

func (*ModelSequenceBatching_ControlInput) XXX_Unmarshal 

func (m *ModelSequenceBatching_ControlInput) XXX_Unmarshal(b []byte) error

type ModelSequenceBatching_Control_Kind 

type ModelSequenceBatching_Control_Kind int32

@@ @@ .. cpp:enum:: Kind @@ @@ The kind of the control. @@ 

const (
	//@@      .. cpp:enumerator:: Kind::CONTROL_SEQUENCE_START = 0
	//@@
	//@@         A new sequence is/is-not starting. If true a sequence is
	//@@         starting, if false a sequence is continuing.
	//@@
	ModelSequenceBatching_Control_CONTROL_SEQUENCE_START ModelSequenceBatching_Control_Kind = 0
	//@@      .. cpp:enumerator:: Kind::CONTROL_SEQUENCE_READY = 1
	//@@
	//@@         A sequence is/is-not ready for inference. If true the
	//@@         input tensor data is valid and should be used. If false
	//@@         the input tensor data is invalid and inferencing should
	//@@         be "skipped".
	//@@
	ModelSequenceBatching_Control_CONTROL_SEQUENCE_READY ModelSequenceBatching_Control_Kind = 1
)

func (ModelSequenceBatching_Control_Kind) EnumDescriptor 

func (ModelSequenceBatching_Control_Kind) EnumDescriptor() ([]byte, []int)

func (ModelSequenceBatching_Control_Kind) String 

func (x ModelSequenceBatching_Control_Kind) String() string

type ModelStatus 

type ModelStatus struct {
	//@@  .. cpp:var:: ModelConfig config
	//@@
	//@@     The configuration for the model.
	//@@
	Config *ModelConfig `protobuf:"bytes,1,opt,name=config,proto3" json:"config,omitempty"`
	//@@  .. cpp:var:: map<int64, ModelVersionStatus> version_status
	//@@
	//@@     Duration statistics for each version of the model, as a map
	//@@     from version to the status. A version will not occur in the map
	//@@     unless there has been at least one inference request of
	//@@     that model version. A version of -1 indicates the status is
	//@@     for requests for which the version could not be determined.
	//@@
	VersionStatus        map[int64]*ModelVersionStatus `` /* 189-byte string literal not displayed */
	XXX_NoUnkeyedLiteral struct{}                      `json:"-"`
	XXX_unrecognized     []byte                        `json:"-"`
	XXX_sizecache        int32                         `json:"-"`
}

@@ @@.. cpp:var:: message ModelStatus @@ @@ Status for a model. @@

func (*ModelStatus) Descriptor 

func (*ModelStatus) Descriptor() ([]byte, []int)

func (*ModelStatus) GetConfig 

func (m *ModelStatus) GetConfig() *ModelConfig

func (*ModelStatus) GetVersionStatus 

func (m *ModelStatus) GetVersionStatus() map[int64]*ModelVersionStatus

func (*ModelStatus) ProtoMessage 

func (*ModelStatus) ProtoMessage()

func (*ModelStatus) Reset 

func (m *ModelStatus) Reset()

func (*ModelStatus) String 

func (m *ModelStatus) String() string

func (*ModelStatus) XXX_DiscardUnknown 

func (m *ModelStatus) XXX_DiscardUnknown()

func (*ModelStatus) XXX_Marshal 

func (m *ModelStatus) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelStatus) XXX_Merge 

func (m *ModelStatus) XXX_Merge(src proto.Message)

func (*ModelStatus) XXX_Size 

func (m *ModelStatus) XXX_Size() int

func (*ModelStatus) XXX_Unmarshal 

func (m *ModelStatus) XXX_Unmarshal(b []byte) error

type ModelTensorReshape 

type ModelTensorReshape struct {
	//@@  .. cpp:var:: int64 shape (repeated)
	//@@
	//@@     The shape to use for reshaping.
	//@@
	Shape                []int64  `protobuf:"varint,1,rep,packed,name=shape,proto3" json:"shape,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@.. cpp:var:: message ModelTensorReshape @@ @@ Reshape specification for input and output tensors. @@

func (*ModelTensorReshape) Descriptor 

func (*ModelTensorReshape) Descriptor() ([]byte, []int)

func (*ModelTensorReshape) GetShape 

func (m *ModelTensorReshape) GetShape() []int64

func (*ModelTensorReshape) ProtoMessage 

func (*ModelTensorReshape) ProtoMessage()

func (*ModelTensorReshape) Reset 

func (m *ModelTensorReshape) Reset()

func (*ModelTensorReshape) String 

func (m *ModelTensorReshape) String() string

func (*ModelTensorReshape) XXX_DiscardUnknown 

func (m *ModelTensorReshape) XXX_DiscardUnknown()

func (*ModelTensorReshape) XXX_Marshal 

func (m *ModelTensorReshape) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelTensorReshape) XXX_Merge 

func (m *ModelTensorReshape) XXX_Merge(src proto.Message)

func (*ModelTensorReshape) XXX_Size 

func (m *ModelTensorReshape) XXX_Size() int

func (*ModelTensorReshape) XXX_Unmarshal 

func (m *ModelTensorReshape) XXX_Unmarshal(b []byte) error

type ModelVersionPolicy 

type ModelVersionPolicy struct {
	//@@  .. cpp:var:: oneof policy_choice
	//@@
	//@@     Each model must implement only a single version policy. The
	//@@     default policy is 'Latest'.
	//@@
	//
	// Types that are valid to be assigned to PolicyChoice:
	//	*ModelVersionPolicy_Latest_
	//	*ModelVersionPolicy_All_
	//	*ModelVersionPolicy_Specific_
	PolicyChoice         isModelVersionPolicy_PolicyChoice `protobuf_oneof:"policy_choice"`
	XXX_NoUnkeyedLiteral struct{}                          `json:"-"`
	XXX_unrecognized     []byte                            `json:"-"`
	XXX_sizecache        int32                             `json:"-"`
}

@@ @@.. cpp:var:: message ModelVersionPolicy @@ @@ Policy indicating which versions of a model should be made @@ available by the inference server. @@

func (*ModelVersionPolicy) Descriptor 

func (*ModelVersionPolicy) Descriptor() ([]byte, []int)

func (*ModelVersionPolicy) GetAll 

func (m *ModelVersionPolicy) GetAll() *ModelVersionPolicy_All

func (*ModelVersionPolicy) GetLatest 

func (m *ModelVersionPolicy) GetLatest() *ModelVersionPolicy_Latest

func (*ModelVersionPolicy) GetPolicyChoice 

func (m *ModelVersionPolicy) GetPolicyChoice() isModelVersionPolicy_PolicyChoice

func (*ModelVersionPolicy) GetSpecific 

func (m *ModelVersionPolicy) GetSpecific() *ModelVersionPolicy_Specific

func (*ModelVersionPolicy) ProtoMessage 

func (*ModelVersionPolicy) ProtoMessage()

func (*ModelVersionPolicy) Reset 

func (m *ModelVersionPolicy) Reset()

func (*ModelVersionPolicy) String 

func (m *ModelVersionPolicy) String() string

func (*ModelVersionPolicy) XXX_DiscardUnknown 

func (m *ModelVersionPolicy) XXX_DiscardUnknown()

func (*ModelVersionPolicy) XXX_Marshal 

func (m *ModelVersionPolicy) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelVersionPolicy) XXX_Merge 

func (m *ModelVersionPolicy) XXX_Merge(src proto.Message)

func (*ModelVersionPolicy) XXX_OneofWrappers 

func (*ModelVersionPolicy) XXX_OneofWrappers() []interface{}

XXX_OneofWrappers is for the internal use of the proto package.

func (*ModelVersionPolicy) XXX_Size 

func (m *ModelVersionPolicy) XXX_Size() int

func (*ModelVersionPolicy) XXX_Unmarshal 

func (m *ModelVersionPolicy) XXX_Unmarshal(b []byte) error

type ModelVersionPolicy_All 

type ModelVersionPolicy_All struct {
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ .. cpp:var:: message All @@ @@ Serve all versions of the model. @@

func (*ModelVersionPolicy_All) Descriptor 

func (*ModelVersionPolicy_All) Descriptor() ([]byte, []int)

func (*ModelVersionPolicy_All) ProtoMessage 

func (*ModelVersionPolicy_All) ProtoMessage()

func (*ModelVersionPolicy_All) Reset 

func (m *ModelVersionPolicy_All) Reset()

func (*ModelVersionPolicy_All) String 

func (m *ModelVersionPolicy_All) String() string

func (*ModelVersionPolicy_All) XXX_DiscardUnknown 

func (m *ModelVersionPolicy_All) XXX_DiscardUnknown()

func (*ModelVersionPolicy_All) XXX_Marshal 

func (m *ModelVersionPolicy_All) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelVersionPolicy_All) XXX_Merge 

func (m *ModelVersionPolicy_All) XXX_Merge(src proto.Message)

func (*ModelVersionPolicy_All) XXX_Size 

func (m *ModelVersionPolicy_All) XXX_Size() int

func (*ModelVersionPolicy_All) XXX_Unmarshal 

func (m *ModelVersionPolicy_All) XXX_Unmarshal(b []byte) error

type ModelVersionPolicy_All_ 

type ModelVersionPolicy_All_ struct {
	All *ModelVersionPolicy_All `protobuf:"bytes,2,opt,name=all,proto3,oneof"`
}

type ModelVersionPolicy_Latest 

type ModelVersionPolicy_Latest struct {
	//@@    .. cpp:var:: uint32 num_versions
	//@@
	//@@       Serve only the 'num_versions' highest-numbered versions. T
	//@@       The default value of 'num_versions' is 1, indicating that by
	//@@       default only the single highest-number version of a
	//@@       model will be served.
	//@@
	NumVersions          uint32   `protobuf:"varint,1,opt,name=num_versions,json=numVersions,proto3" json:"num_versions,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ .. cpp:var:: message Latest @@ @@ Serve only the latest version(s) of a model. This is @@ the default policy. @@

func (*ModelVersionPolicy_Latest) Descriptor 

func (*ModelVersionPolicy_Latest) Descriptor() ([]byte, []int)

func (*ModelVersionPolicy_Latest) GetNumVersions 

func (m *ModelVersionPolicy_Latest) GetNumVersions() uint32

func (*ModelVersionPolicy_Latest) ProtoMessage 

func (*ModelVersionPolicy_Latest) ProtoMessage()

func (*ModelVersionPolicy_Latest) Reset 

func (m *ModelVersionPolicy_Latest) Reset()

func (*ModelVersionPolicy_Latest) String 

func (m *ModelVersionPolicy_Latest) String() string

func (*ModelVersionPolicy_Latest) XXX_DiscardUnknown 

func (m *ModelVersionPolicy_Latest) XXX_DiscardUnknown()

func (*ModelVersionPolicy_Latest) XXX_Marshal 

func (m *ModelVersionPolicy_Latest) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelVersionPolicy_Latest) XXX_Merge 

func (m *ModelVersionPolicy_Latest) XXX_Merge(src proto.Message)

func (*ModelVersionPolicy_Latest) XXX_Size 

func (m *ModelVersionPolicy_Latest) XXX_Size() int

func (*ModelVersionPolicy_Latest) XXX_Unmarshal 

func (m *ModelVersionPolicy_Latest) XXX_Unmarshal(b []byte) error

type ModelVersionPolicy_Latest_ 

type ModelVersionPolicy_Latest_ struct {
	Latest *ModelVersionPolicy_Latest `protobuf:"bytes,1,opt,name=latest,proto3,oneof"`
}

type ModelVersionPolicy_Specific 

type ModelVersionPolicy_Specific struct {
	//@@    .. cpp:var:: int64 versions (repeated)
	//@@
	//@@       The specific versions of the model that will be served.
	//@@
	Versions             []int64  `protobuf:"varint,1,rep,packed,name=versions,proto3" json:"versions,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ .. cpp:var:: message Specific @@ @@ Serve only specific versions of the model. @@

func (*ModelVersionPolicy_Specific) Descriptor 

func (*ModelVersionPolicy_Specific) Descriptor() ([]byte, []int)

func (*ModelVersionPolicy_Specific) GetVersions 

func (m *ModelVersionPolicy_Specific) GetVersions() []int64

func (*ModelVersionPolicy_Specific) ProtoMessage 

func (*ModelVersionPolicy_Specific) ProtoMessage()

func (*ModelVersionPolicy_Specific) Reset 

func (m *ModelVersionPolicy_Specific) Reset()

func (*ModelVersionPolicy_Specific) String 

func (m *ModelVersionPolicy_Specific) String() string

func (*ModelVersionPolicy_Specific) XXX_DiscardUnknown 

func (m *ModelVersionPolicy_Specific) XXX_DiscardUnknown()

func (*ModelVersionPolicy_Specific) XXX_Marshal 

func (m *ModelVersionPolicy_Specific) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelVersionPolicy_Specific) XXX_Merge 

func (m *ModelVersionPolicy_Specific) XXX_Merge(src proto.Message)

func (*ModelVersionPolicy_Specific) XXX_Size 

func (m *ModelVersionPolicy_Specific) XXX_Size() int

func (*ModelVersionPolicy_Specific) XXX_Unmarshal 

func (m *ModelVersionPolicy_Specific) XXX_Unmarshal(b []byte) error

type ModelVersionPolicy_Specific_ 

type ModelVersionPolicy_Specific_ struct {
	Specific *ModelVersionPolicy_Specific `protobuf:"bytes,3,opt,name=specific,proto3,oneof"`
}

type ModelVersionStatus 

type ModelVersionStatus struct {
	//@@  .. cpp:var:: ModelReadyState ready_statue
	//@@
	//@@     Current readiness state for the model.
	//@@
	ReadyState ModelReadyState `` /* 136-byte string literal not displayed */
	//@@  .. cpp:var:: map<uint32, InferRequestStats> infer_stats
	//@@
	//@@     Inference statistics for the model, as a map from batch size
	//@@     to the statistics. A batch size will not occur in the map
	//@@     unless there has been at least one inference request of
	//@@     that batch size.
	//@@
	InferStats map[uint32]*InferRequestStats `` /* 180-byte string literal not displayed */
	//@@  .. cpp:var:: uint64 model_execution_count
	//@@
	//@@     Cumulative number of model executions performed for the
	//@@     model. A single model execution performs inferencing for
	//@@     the entire request batch and can perform inferencing for multiple
	//@@     requests if dynamic batching is enabled.
	//@@
	ModelExecutionCount uint64 `protobuf:"varint,3,opt,name=model_execution_count,json=modelExecutionCount,proto3" json:"model_execution_count,omitempty"`
	//@@  .. cpp:var:: uint64 model_inference_count
	//@@
	//@@     Cumulative number of model inferences performed for the
	//@@     model. Each inference in a batched request is counted as
	//@@     an individual inference.
	//@@
	ModelInferenceCount  uint64   `protobuf:"varint,4,opt,name=model_inference_count,json=modelInferenceCount,proto3" json:"model_inference_count,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@.. cpp:var:: message ModelVersionStatus @@ @@ Status for a version of a model. @@

func (*ModelVersionStatus) Descriptor 

func (*ModelVersionStatus) Descriptor() ([]byte, []int)

func (*ModelVersionStatus) GetInferStats 

func (m *ModelVersionStatus) GetInferStats() map[uint32]*InferRequestStats

func (*ModelVersionStatus) GetModelExecutionCount 

func (m *ModelVersionStatus) GetModelExecutionCount() uint64

func (*ModelVersionStatus) GetModelInferenceCount 

func (m *ModelVersionStatus) GetModelInferenceCount() uint64

func (*ModelVersionStatus) GetReadyState 

func (m *ModelVersionStatus) GetReadyState() ModelReadyState

func (*ModelVersionStatus) ProtoMessage 

func (*ModelVersionStatus) ProtoMessage()

func (*ModelVersionStatus) Reset 

func (m *ModelVersionStatus) Reset()

func (*ModelVersionStatus) String 

func (m *ModelVersionStatus) String() string

func (*ModelVersionStatus) XXX_DiscardUnknown 

func (m *ModelVersionStatus) XXX_DiscardUnknown()

func (*ModelVersionStatus) XXX_Marshal 

func (m *ModelVersionStatus) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ModelVersionStatus) XXX_Merge 

func (m *ModelVersionStatus) XXX_Merge(src proto.Message)

func (*ModelVersionStatus) XXX_Size 

func (m *ModelVersionStatus) XXX_Size() int

func (*ModelVersionStatus) XXX_Unmarshal 

func (m *ModelVersionStatus) XXX_Unmarshal(b []byte) error

type ProfileRequest 

type ProfileRequest struct {
	//@@
	//@@  .. cpp:var:: string cmd
	//@@
	//@@     The requested profiling action: 'start' requests that GPU
	//@@     profiling be enabled on all GPUs controlled by the inference
	//@@     server; 'stop' requests that GPU profiling be disabled on all GPUs
	//@@     controlled by the inference server.
	//@@
	Cmd                  string   `protobuf:"bytes,1,opt,name=cmd,proto3" json:"cmd,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@.. cpp:var:: message ProfileRequest @@ @@ Request message for Profile gRPC endpoint. @@

func (*ProfileRequest) Descriptor 

func (*ProfileRequest) Descriptor() ([]byte, []int)

func (*ProfileRequest) GetCmd 

func (m *ProfileRequest) GetCmd() string

func (*ProfileRequest) ProtoMessage 

func (*ProfileRequest) ProtoMessage()

func (*ProfileRequest) Reset 

func (m *ProfileRequest) Reset()

func (*ProfileRequest) String 

func (m *ProfileRequest) String() string

func (*ProfileRequest) XXX_DiscardUnknown 

func (m *ProfileRequest) XXX_DiscardUnknown()

func (*ProfileRequest) XXX_Marshal 

func (m *ProfileRequest) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ProfileRequest) XXX_Merge 

func (m *ProfileRequest) XXX_Merge(src proto.Message)

func (*ProfileRequest) XXX_Size 

func (m *ProfileRequest) XXX_Size() int

func (*ProfileRequest) XXX_Unmarshal 

func (m *ProfileRequest) XXX_Unmarshal(b []byte) error

type ProfileRequestStats 

type ProfileRequestStats struct {
	//@@  .. cpp:var:: StatDuration success
	//@@
	//@@     Total time required to handle successful Profile requests, not
	//@@     including HTTP or gRPC endpoint termination time.
	//@@
	Success              *StatDuration `protobuf:"bytes,1,opt,name=success,proto3" json:"success,omitempty"`
	XXX_NoUnkeyedLiteral struct{}      `json:"-"`
	XXX_unrecognized     []byte        `json:"-"`
	XXX_sizecache        int32         `json:"-"`
}

@@ @@.. cpp:var:: message ProfileRequestStats @@ @@ Statistics collected for Profile requests. @@

func (*ProfileRequestStats) Descriptor 

func (*ProfileRequestStats) Descriptor() ([]byte, []int)

func (*ProfileRequestStats) GetSuccess 

func (m *ProfileRequestStats) GetSuccess() *StatDuration

func (*ProfileRequestStats) ProtoMessage 

func (*ProfileRequestStats) ProtoMessage()

func (*ProfileRequestStats) Reset 

func (m *ProfileRequestStats) Reset()

func (*ProfileRequestStats) String 

func (m *ProfileRequestStats) String() string

func (*ProfileRequestStats) XXX_DiscardUnknown 

func (m *ProfileRequestStats) XXX_DiscardUnknown()

func (*ProfileRequestStats) XXX_Marshal 

func (m *ProfileRequestStats) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ProfileRequestStats) XXX_Merge 

func (m *ProfileRequestStats) XXX_Merge(src proto.Message)

func (*ProfileRequestStats) XXX_Size 

func (m *ProfileRequestStats) XXX_Size() int

func (*ProfileRequestStats) XXX_Unmarshal 

func (m *ProfileRequestStats) XXX_Unmarshal(b []byte) error

type ProfileResponse 

type ProfileResponse struct {
	//@@
	//@@  .. cpp:var:: RequestStatus request_status
	//@@
	//@@     The status of the request, indicating success or failure.
	//@@
	RequestStatus        *RequestStatus `protobuf:"bytes,1,opt,name=request_status,json=requestStatus,proto3" json:"request_status,omitempty"`
	XXX_NoUnkeyedLiteral struct{}       `json:"-"`
	XXX_unrecognized     []byte         `json:"-"`
	XXX_sizecache        int32          `json:"-"`
}

@@ @@.. cpp:var:: message ProfileResponse @@ @@ Response message for Profile gRPC endpoint. @@

func (*ProfileResponse) Descriptor 

func (*ProfileResponse) Descriptor() ([]byte, []int)

func (*ProfileResponse) GetRequestStatus 

func (m *ProfileResponse) GetRequestStatus() *RequestStatus

func (*ProfileResponse) ProtoMessage 

func (*ProfileResponse) ProtoMessage()

func (*ProfileResponse) Reset 

func (m *ProfileResponse) Reset()

func (*ProfileResponse) String 

func (m *ProfileResponse) String() string

func (*ProfileResponse) XXX_DiscardUnknown 

func (m *ProfileResponse) XXX_DiscardUnknown()

func (*ProfileResponse) XXX_Marshal 

func (m *ProfileResponse) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ProfileResponse) XXX_Merge 

func (m *ProfileResponse) XXX_Merge(src proto.Message)

func (*ProfileResponse) XXX_Size 

func (m *ProfileResponse) XXX_Size() int

func (*ProfileResponse) XXX_Unmarshal 

func (m *ProfileResponse) XXX_Unmarshal(b []byte) error

type RequestStatus 

type RequestStatus struct {
	//@@  .. cpp:var:: RequestStatusCode code
	//@@
	//@@     The status code.
	//@@
	Code RequestStatusCode `protobuf:"varint,1,opt,name=code,proto3,enum=nvidia.inferenceserver.RequestStatusCode" json:"code,omitempty"`
	//@@  .. cpp:var:: string msg
	//@@
	//@@     The optional status message.
	//@@
	Msg string `protobuf:"bytes,2,opt,name=msg,proto3" json:"msg,omitempty"`
	//@@  .. cpp:var:: string server_id
	//@@
	//@@     The identifying string for the server that is returning
	//@@     this status.
	//@@
	ServerId string `protobuf:"bytes,3,opt,name=server_id,json=serverId,proto3" json:"server_id,omitempty"`
	//@@  .. cpp:var:: string request_id
	//@@
	//@@     Unique identifier for the request. Value 0 (zero) indicates
	//@@     the request ID is not known.
	//@@
	RequestId            uint64   `protobuf:"varint,4,opt,name=request_id,json=requestId,proto3" json:"request_id,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@.. cpp:var:: message RequestStatus @@ @@ Status returned for all inference server requests. The @@ RequestStatus provides a :cpp:enum:`RequestStatusCode`, an @@ optional status message, and server and request IDs. @@

func (*RequestStatus) Descriptor 

func (*RequestStatus) Descriptor() ([]byte, []int)

func (*RequestStatus) GetCode 

func (m *RequestStatus) GetCode() RequestStatusCode

func (*RequestStatus) GetMsg 

func (m *RequestStatus) GetMsg() string

func (*RequestStatus) GetRequestId 

func (m *RequestStatus) GetRequestId() uint64

func (*RequestStatus) GetServerId 

func (m *RequestStatus) GetServerId() string

func (*RequestStatus) ProtoMessage 

func (*RequestStatus) ProtoMessage()

func (*RequestStatus) Reset 

func (m *RequestStatus) Reset()

func (*RequestStatus) String 

func (m *RequestStatus) String() string

func (*RequestStatus) XXX_DiscardUnknown 

func (m *RequestStatus) XXX_DiscardUnknown()

func (*RequestStatus) XXX_Marshal 

func (m *RequestStatus) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*RequestStatus) XXX_Merge 

func (m *RequestStatus) XXX_Merge(src proto.Message)

func (*RequestStatus) XXX_Size 

func (m *RequestStatus) XXX_Size() int

func (*RequestStatus) XXX_Unmarshal 

func (m *RequestStatus) XXX_Unmarshal(b []byte) error

type RequestStatusCode 

type RequestStatusCode int32

@@ @@.. cpp:enum:: RequestStatusCode @@ @@ Status codes returned for inference server requests. The @@ :cpp:enumerator:`RequestStatusCode::SUCCESS` status code indicates @@ not error, all other codes indicate an error. @@ 

const (
	//@@  .. cpp:enumerator:: RequestStatusCode::INVALID = 0
	//@@
	//@@     Invalid status. Used internally but should not be returned as
	//@@     part of a :cpp:var:`RequestStatus`.
	//@@
	RequestStatusCode_INVALID RequestStatusCode = 0
	//@@  .. cpp:enumerator:: RequestStatusCode::SUCCESS = 1
	//@@
	//@@     Error code indicating success.
	//@@
	RequestStatusCode_SUCCESS RequestStatusCode = 1
	//@@  .. cpp:enumerator:: RequestStatusCode::UNKNOWN = 2
	//@@
	//@@     Error code indicating an unknown failure.
	//@@
	RequestStatusCode_UNKNOWN RequestStatusCode = 2
	//@@  .. cpp:enumerator:: RequestStatusCode::INTERNAL = 3
	//@@
	//@@     Error code indicating an internal failure.
	//@@
	RequestStatusCode_INTERNAL RequestStatusCode = 3
	//@@  .. cpp:enumerator:: RequestStatusCode::NOT_FOUND = 4
	//@@
	//@@     Error code indicating a resource or request was not found.
	//@@
	RequestStatusCode_NOT_FOUND RequestStatusCode = 4
	//@@  .. cpp:enumerator:: RequestStatusCode::INVALID_ARG = 5
	//@@
	//@@     Error code indicating a failure caused by an unknown argument or
	//@@     value.
	//@@
	RequestStatusCode_INVALID_ARG RequestStatusCode = 5
	//@@  .. cpp:enumerator:: RequestStatusCode::UNAVAILABLE = 6
	//@@
	//@@     Error code indicating an unavailable resource.
	//@@
	RequestStatusCode_UNAVAILABLE RequestStatusCode = 6
	//@@  .. cpp:enumerator:: RequestStatusCode::UNSUPPORTED = 7
	//@@
	//@@     Error code indicating an unsupported request or operation.
	//@@
	RequestStatusCode_UNSUPPORTED RequestStatusCode = 7
	//@@  .. cpp:enumerator:: RequestStatusCode::ALREADY_EXISTS = 8
	//@@
	//@@     Error code indicating an already existing resource.
	//@@
	RequestStatusCode_ALREADY_EXISTS RequestStatusCode = 8
)

func (RequestStatusCode) EnumDescriptor 

func (RequestStatusCode) EnumDescriptor() ([]byte, []int)

func (RequestStatusCode) String 

func (x RequestStatusCode) String() string

type ServerReadyState 

type ServerReadyState int32

@@ @@.. cpp:enum:: ServerReadyState @@ @@ Readiness status for the inference server. @@ 

const (
	//@@  .. cpp:enumerator:: ServerReadyState::SERVER_INVALID = 0
	//@@
	//@@     The server is in an invalid state and will likely not
	//@@     response correctly to any requests.
	//@@
	ServerReadyState_SERVER_INVALID ServerReadyState = 0
	//@@  .. cpp:enumerator:: ServerReadyState::SERVER_INITIALIZING = 1
	//@@
	//@@     The server is initializing.
	//@@
	ServerReadyState_SERVER_INITIALIZING ServerReadyState = 1
	//@@  .. cpp:enumerator:: ServerReadyState::SERVER_READY = 2
	//@@
	//@@     The server is ready and accepting requests.
	//@@
	ServerReadyState_SERVER_READY ServerReadyState = 2
	//@@  .. cpp:enumerator:: ServerReadyState::SERVER_EXITING = 3
	//@@
	//@@     The server is exiting and will not respond to requests.
	//@@
	ServerReadyState_SERVER_EXITING ServerReadyState = 3
	//@@  .. cpp:enumerator:: ServerReadyState::SERVER_FAILED_TO_INITIALIZE = 10
	//@@
	//@@     The server did not initialize correctly. Most requests will fail.
	//@@
	ServerReadyState_SERVER_FAILED_TO_INITIALIZE ServerReadyState = 10
)

func (ServerReadyState) EnumDescriptor 

func (ServerReadyState) EnumDescriptor() ([]byte, []int)

func (ServerReadyState) String 

func (x ServerReadyState) String() string

type ServerStatus 

type ServerStatus struct {
	//@@  .. cpp:var:: string id
	//@@
	//@@     The server's ID.
	//@@
	Id string `protobuf:"bytes,1,opt,name=id,proto3" json:"id,omitempty"`
	//@@  .. cpp:var:: string version
	//@@
	//@@     The server's version.
	//@@
	Version string `protobuf:"bytes,2,opt,name=version,proto3" json:"version,omitempty"`
	//@@  .. cpp:var:: ServerReadyState ready_state
	//@@
	//@@     Current readiness state for the server.
	//@@
	ReadyState ServerReadyState `` /* 137-byte string literal not displayed */
	//@@  .. cpp:var:: uint64 uptime_ns
	//@@
	//@@     Server uptime in nanoseconds.
	//@@
	UptimeNs uint64 `protobuf:"varint,3,opt,name=uptime_ns,json=uptimeNs,proto3" json:"uptime_ns,omitempty"`
	//@@  .. cpp:var:: map<string, ModelStatus> model_status
	//@@
	//@@     Status for each model, as a map from model name to the
	//@@     status.
	//@@
	ModelStatus map[string]*ModelStatus `` /* 182-byte string literal not displayed */
	//@@  .. cpp:var:: StatusRequestStats status_stats
	//@@
	//@@     Statistics for Status requests.
	//@@
	StatusStats *StatusRequestStats `protobuf:"bytes,5,opt,name=status_stats,json=statusStats,proto3" json:"status_stats,omitempty"`
	//@@  .. cpp:var:: ProfileRequestStats profile_stats
	//@@
	//@@     Statistics for Profile requests.
	//@@
	ProfileStats *ProfileRequestStats `protobuf:"bytes,6,opt,name=profile_stats,json=profileStats,proto3" json:"profile_stats,omitempty"`
	//@@  .. cpp:var:: HealthRequestStats health_stats
	//@@
	//@@     Statistics for Health requests.
	//@@
	HealthStats          *HealthRequestStats `protobuf:"bytes,8,opt,name=health_stats,json=healthStats,proto3" json:"health_stats,omitempty"`
	XXX_NoUnkeyedLiteral struct{}            `json:"-"`
	XXX_unrecognized     []byte              `json:"-"`
	XXX_sizecache        int32               `json:"-"`
}

@@ @@.. cpp:var:: message ServerStatus @@ @@ Status for the inference server. @@

func (*ServerStatus) Descriptor 

func (*ServerStatus) Descriptor() ([]byte, []int)

func (*ServerStatus) GetHealthStats 

func (m *ServerStatus) GetHealthStats() *HealthRequestStats

func (*ServerStatus) GetId 

func (m *ServerStatus) GetId() string

func (*ServerStatus) GetModelStatus 

func (m *ServerStatus) GetModelStatus() map[string]*ModelStatus

func (*ServerStatus) GetProfileStats 

func (m *ServerStatus) GetProfileStats() *ProfileRequestStats

func (*ServerStatus) GetReadyState 

func (m *ServerStatus) GetReadyState() ServerReadyState

func (*ServerStatus) GetStatusStats 

func (m *ServerStatus) GetStatusStats() *StatusRequestStats

func (*ServerStatus) GetUptimeNs 

func (m *ServerStatus) GetUptimeNs() uint64

func (*ServerStatus) GetVersion 

func (m *ServerStatus) GetVersion() string

func (*ServerStatus) ProtoMessage 

func (*ServerStatus) ProtoMessage()

func (*ServerStatus) Reset 

func (m *ServerStatus) Reset()

func (*ServerStatus) String 

func (m *ServerStatus) String() string

func (*ServerStatus) XXX_DiscardUnknown 

func (m *ServerStatus) XXX_DiscardUnknown()

func (*ServerStatus) XXX_Marshal 

func (m *ServerStatus) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*ServerStatus) XXX_Merge 

func (m *ServerStatus) XXX_Merge(src proto.Message)

func (*ServerStatus) XXX_Size 

func (m *ServerStatus) XXX_Size() int

func (*ServerStatus) XXX_Unmarshal 

func (m *ServerStatus) XXX_Unmarshal(b []byte) error

type StatDuration 

type StatDuration struct {
	//@@  .. cpp:var:: uint64 count
	//@@
	//@@     Cumulative number of times this metric occurred.
	//@@
	Count uint64 `protobuf:"varint,1,opt,name=count,proto3" json:"count,omitempty"`
	//@@  .. cpp:var:: uint64 total_time_ns
	//@@
	//@@     Total collected duration of this metric in nanoseconds.
	//@@
	TotalTimeNs          uint64   `protobuf:"varint,2,opt,name=total_time_ns,json=totalTimeNs,proto3" json:"total_time_ns,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@.. cpp:var:: message StatDuration @@ @@ Statistic collecting a duration metric. @@

func (*StatDuration) Descriptor 

func (*StatDuration) Descriptor() ([]byte, []int)

func (*StatDuration) GetCount 

func (m *StatDuration) GetCount() uint64

func (*StatDuration) GetTotalTimeNs 

func (m *StatDuration) GetTotalTimeNs() uint64

func (*StatDuration) ProtoMessage 

func (*StatDuration) ProtoMessage()

func (*StatDuration) Reset 

func (m *StatDuration) Reset()

func (*StatDuration) String 

func (m *StatDuration) String() string

func (*StatDuration) XXX_DiscardUnknown 

func (m *StatDuration) XXX_DiscardUnknown()

func (*StatDuration) XXX_Marshal 

func (m *StatDuration) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*StatDuration) XXX_Merge 

func (m *StatDuration) XXX_Merge(src proto.Message)

func (*StatDuration) XXX_Size 

func (m *StatDuration) XXX_Size() int

func (*StatDuration) XXX_Unmarshal 

func (m *StatDuration) XXX_Unmarshal(b []byte) error

type StatusRequest 

type StatusRequest struct {
	//@@
	//@@  .. cpp:var:: string model_name
	//@@
	//@@     The specific model status to be returned. If empty return status
	//@@     for all models.
	//@@
	ModelName            string   `protobuf:"bytes,1,opt,name=model_name,json=modelName,proto3" json:"model_name,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

@@ @@.. cpp:var:: message StatusRequest @@ @@ Request message for Status gRPC endpoint. @@

func (*StatusRequest) Descriptor 

func (*StatusRequest) Descriptor() ([]byte, []int)

func (*StatusRequest) GetModelName 

func (m *StatusRequest) GetModelName() string

func (*StatusRequest) ProtoMessage 

func (*StatusRequest) ProtoMessage()

func (*StatusRequest) Reset 

func (m *StatusRequest) Reset()

func (*StatusRequest) String 

func (m *StatusRequest) String() string

func (*StatusRequest) XXX_DiscardUnknown 

func (m *StatusRequest) XXX_DiscardUnknown()

func (*StatusRequest) XXX_Marshal 

func (m *StatusRequest) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*StatusRequest) XXX_Merge 

func (m *StatusRequest) XXX_Merge(src proto.Message)

func (*StatusRequest) XXX_Size 

func (m *StatusRequest) XXX_Size() int

func (*StatusRequest) XXX_Unmarshal 

func (m *StatusRequest) XXX_Unmarshal(b []byte) error

type StatusRequestStats 

type StatusRequestStats struct {
	//@@  .. cpp:var:: StatDuration success
	//@@
	//@@     Total time required to handle successful Status requests, not
	//@@     including HTTP or gRPC endpoint termination time.
	//@@
	Success              *StatDuration `protobuf:"bytes,1,opt,name=success,proto3" json:"success,omitempty"`
	XXX_NoUnkeyedLiteral struct{}      `json:"-"`
	XXX_unrecognized     []byte        `json:"-"`
	XXX_sizecache        int32         `json:"-"`
}

@@ @@.. cpp:var:: message StatusRequestStats @@ @@ Statistics collected for Status requests. @@

func (*StatusRequestStats) Descriptor 

func (*StatusRequestStats) Descriptor() ([]byte, []int)

func (*StatusRequestStats) GetSuccess 

func (m *StatusRequestStats) GetSuccess() *StatDuration

func (*StatusRequestStats) ProtoMessage 

func (*StatusRequestStats) ProtoMessage()

func (*StatusRequestStats) Reset 

func (m *StatusRequestStats) Reset()

func (*StatusRequestStats) String 

func (m *StatusRequestStats) String() string

func (*StatusRequestStats) XXX_DiscardUnknown 

func (m *StatusRequestStats) XXX_DiscardUnknown()

func (*StatusRequestStats) XXX_Marshal 

func (m *StatusRequestStats) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*StatusRequestStats) XXX_Merge 

func (m *StatusRequestStats) XXX_Merge(src proto.Message)

func (*StatusRequestStats) XXX_Size 

func (m *StatusRequestStats) XXX_Size() int

func (*StatusRequestStats) XXX_Unmarshal 

func (m *StatusRequestStats) XXX_Unmarshal(b []byte) error

type StatusResponse 

type StatusResponse struct {
	//@@
	//@@  .. cpp:var:: RequestStatus request_status
	//@@
	//@@     The status of the request, indicating success or failure.
	//@@
	RequestStatus *RequestStatus `protobuf:"bytes,1,opt,name=request_status,json=requestStatus,proto3" json:"request_status,omitempty"`
	//@@
	//@@  .. cpp:var:: ServerStatus server_status
	//@@
	//@@     The server and model status.
	//@@
	ServerStatus         *ServerStatus `protobuf:"bytes,2,opt,name=server_status,json=serverStatus,proto3" json:"server_status,omitempty"`
	XXX_NoUnkeyedLiteral struct{}      `json:"-"`
	XXX_unrecognized     []byte        `json:"-"`
	XXX_sizecache        int32         `json:"-"`
}

@@ @@.. cpp:var:: message StatusResponse @@ @@ Response message for Status gRPC endpoint. @@

func (*StatusResponse) Descriptor 

func (*StatusResponse) Descriptor() ([]byte, []int)

func (*StatusResponse) GetRequestStatus 

func (m *StatusResponse) GetRequestStatus() *RequestStatus

func (*StatusResponse) GetServerStatus 

func (m *StatusResponse) GetServerStatus() *ServerStatus

func (*StatusResponse) ProtoMessage 

func (*StatusResponse) ProtoMessage()

func (*StatusResponse) Reset 

func (m *StatusResponse) Reset()

func (*StatusResponse) String 

func (m *StatusResponse) String() string

func (*StatusResponse) XXX_DiscardUnknown 

func (m *StatusResponse) XXX_DiscardUnknown()

func (*StatusResponse) XXX_Marshal 

func (m *StatusResponse) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*StatusResponse) XXX_Merge 

func (m *StatusResponse) XXX_Merge(src proto.Message)

func (*StatusResponse) XXX_Size 

func (m *StatusResponse) XXX_Size() int

func (*StatusResponse) XXX_Unmarshal 

func (m *StatusResponse) XXX_Unmarshal(b []byte) error

type UnimplementedGRPCServiceServer 

type UnimplementedGRPCServiceServer struct {
}

UnimplementedGRPCServiceServer can be embedded to have forward compatible implementations.

func (*UnimplementedGRPCServiceServer) Health 

func (*UnimplementedGRPCServiceServer) Health(ctx context.Context, req *HealthRequest) (*HealthResponse, error)

func (*UnimplementedGRPCServiceServer) Infer 

func (*UnimplementedGRPCServiceServer) Infer(ctx context.Context, req *InferRequest) (*InferResponse, error)

func (*UnimplementedGRPCServiceServer) Profile 

func (*UnimplementedGRPCServiceServer) Profile(ctx context.Context, req *ProfileRequest) (*ProfileResponse, error)

func (*UnimplementedGRPCServiceServer) Status 

func (*UnimplementedGRPCServiceServer) Status(ctx context.Context, req *StatusRequest) (*StatusResponse, error)

func (*UnimplementedGRPCServiceServer) StreamInfer 

func (*UnimplementedGRPCServiceServer) StreamInfer(srv GRPCService_StreamInferServer) error

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.