triton

package
v2.0.0 Latest Latest
Warning

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

 Go to latest Published: Dec 2, 2022 License: Apache-2.0 Imports: 4 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",
	}
	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,
	}
)

Enum value maps for DataType.

View Source 
var (
	ModelInstanceGroup_Kind_name = map[int32]string{
		0: "KIND_AUTO",
		1: "KIND_GPU",
		2: "KIND_CPU",
		3: "KIND_MODEL",
	}
	ModelInstanceGroup_Kind_value = map[string]int32{
		"KIND_AUTO":  0,
		"KIND_GPU":   1,
		"KIND_CPU":   2,
		"KIND_MODEL": 3,
	}
)

Enum value maps for ModelInstanceGroup_Kind.

View Source 
var (
	ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind_name = map[int32]string{
		0: "KIND_NVDLA",
	}
	ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind_value = map[string]int32{
		"KIND_NVDLA": 0,
	}
)

Enum value maps for ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind.

View Source 
var (
	ModelInput_Format_name = map[int32]string{
		0: "FORMAT_NONE",
		1: "FORMAT_NHWC",
		2: "FORMAT_NCHW",
	}
	ModelInput_Format_value = map[string]int32{
		"FORMAT_NONE": 0,
		"FORMAT_NHWC": 1,
		"FORMAT_NCHW": 2,
	}
)

Enum value maps for ModelInput_Format.

View Source 
var (
	BatchInput_Kind_name = map[int32]string{
		0: "BATCH_ELEMENT_COUNT",
		1: "BATCH_ACCUMULATED_ELEMENT_COUNT",
		2: "BATCH_ACCUMULATED_ELEMENT_COUNT_WITH_ZERO",
		3: "BATCH_MAX_ELEMENT_COUNT_AS_SHAPE",
	}
	BatchInput_Kind_value = map[string]int32{
		"BATCH_ELEMENT_COUNT":                       0,
		"BATCH_ACCUMULATED_ELEMENT_COUNT":           1,
		"BATCH_ACCUMULATED_ELEMENT_COUNT_WITH_ZERO": 2,
		"BATCH_MAX_ELEMENT_COUNT_AS_SHAPE":          3,
	}
)

Enum value maps for BatchInput_Kind.

View Source 
var (
	BatchOutput_Kind_name = map[int32]string{
		0: "BATCH_SCATTER_WITH_INPUT_SHAPE",
	}
	BatchOutput_Kind_value = map[string]int32{
		"BATCH_SCATTER_WITH_INPUT_SHAPE": 0,
	}
)

Enum value maps for BatchOutput_Kind.

View Source 
var (
	ModelOptimizationPolicy_ModelPriority_name = map[int32]string{
		0: "PRIORITY_DEFAULT",
		1: "PRIORITY_MAX",
		2: "PRIORITY_MIN",
	}
	ModelOptimizationPolicy_ModelPriority_value = map[string]int32{
		"PRIORITY_DEFAULT": 0,
		"PRIORITY_MAX":     1,
		"PRIORITY_MIN":     2,
	}
)

Enum value maps for ModelOptimizationPolicy_ModelPriority.

View Source 
var (
	ModelQueuePolicy_TimeoutAction_name = map[int32]string{
		0: "REJECT",
		1: "DELAY",
	}
	ModelQueuePolicy_TimeoutAction_value = map[string]int32{
		"REJECT": 0,
		"DELAY":  1,
	}
)

Enum value maps for ModelQueuePolicy_TimeoutAction.

View Source 
var (
	ModelSequenceBatching_Control_Kind_name = map[int32]string{
		0: "CONTROL_SEQUENCE_START",
		1: "CONTROL_SEQUENCE_READY",
		2: "CONTROL_SEQUENCE_END",
		3: "CONTROL_SEQUENCE_CORRID",
	}
	ModelSequenceBatching_Control_Kind_value = map[string]int32{
		"CONTROL_SEQUENCE_START":  0,
		"CONTROL_SEQUENCE_READY":  1,
		"CONTROL_SEQUENCE_END":    2,
		"CONTROL_SEQUENCE_CORRID": 3,
	}
)

Enum value maps for ModelSequenceBatching_Control_Kind.

View Source 
var File_pkg_agent_repository_triton_config_model_config_proto protoreflect.FileDescriptor

Functions

This section is empty.

Types

type BatchInput 

type BatchInput struct {

	//@@    .. cpp:var:: Kind kind
	//@@
	//@@       The kind of this batch input.
	//@@
	Kind BatchInput_Kind `protobuf:"varint,1,opt,name=kind,proto3,enum=inference.BatchInput_Kind" json:"kind,omitempty"`
	//@@    .. cpp:var:: string target_name (repeated)
	//@@
	//@@       The name of the model inputs that the backend will create
	//@@       for this batch input.
	//@@
	TargetName []string `protobuf:"bytes,2,rep,name=target_name,json=targetName,proto3" json:"target_name,omitempty"`
	//@@    .. cpp:var:: DataType data_type
	//@@
	//@@       The input's datatype. The data type can be TYPE_INT32 or
	//@@       TYPE_FP32.
	//@@
	DataType DataType `protobuf:"varint,3,opt,name=data_type,json=dataType,proto3,enum=inference.DataType" json:"data_type,omitempty"`
	//@@    .. cpp:var:: string source_input (repeated)
	//@@
	//@@       The backend derives the value for each batch input from one or
	//@@       more other inputs. 'source_input' gives the names of those
	//@@       inputs.
	//@@
	SourceInput []string `protobuf:"bytes,4,rep,name=source_input,json=sourceInput,proto3" json:"source_input,omitempty"`
	// contains filtered or unexported fields
}

@@ .. cpp:var:: message BatchInput @@ @@ A batch input is an additional input that must be added by @@ the backend based on all the requests in a batch. @@

func (*BatchInput) Descriptor deprecated 

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

Deprecated: Use BatchInput.ProtoReflect.Descriptor instead.

func (*BatchInput) GetDataType 

func (x *BatchInput) GetDataType() DataType

func (*BatchInput) GetKind 

func (x *BatchInput) GetKind() BatchInput_Kind

func (*BatchInput) GetSourceInput 

func (x *BatchInput) GetSourceInput() []string

func (*BatchInput) GetTargetName 

func (x *BatchInput) GetTargetName() []string

func (*BatchInput) ProtoMessage 

func (*BatchInput) ProtoMessage()

func (*BatchInput) ProtoReflect 

func (x *BatchInput) ProtoReflect() protoreflect.Message

func (*BatchInput) Reset 

func (x *BatchInput) Reset()

func (*BatchInput) String 

func (x *BatchInput) String() string

type BatchInput_Kind 

type BatchInput_Kind int32

@@ @@ .. cpp:enum:: Kind @@ @@ The kind of the batch input. @@ 

const (
	//@@      .. cpp:enumerator:: Kind::BATCH_ELEMENT_COUNT = 0
	//@@
	//@@         The element count of the 'source_input' will be added as
	//@@         input with shape [1].
	//@@
	BatchInput_BATCH_ELEMENT_COUNT BatchInput_Kind = 0
	//@@      .. cpp:enumerator:: Kind::BATCH_ACCUMULATED_ELEMENT_COUNT = 1
	//@@
	//@@         The accumulated element count of the 'source_input' will be
	//@@         added as input with shape [1]. For example, if there is a
	//@@         batch of two request, each with 2 elements, an input of value
	//@@         2 will be added to the first request, and an input of value
	//@@         4 will be added to the second request.
	//@@
	BatchInput_BATCH_ACCUMULATED_ELEMENT_COUNT BatchInput_Kind = 1
	//@@      .. cpp:enumerator::
	//@@         Kind::BATCH_ACCUMULATED_ELEMENT_COUNT_WITH_ZERO = 2
	//@@
	//@@         The accumulated element count of the 'source_input' will be
	//@@         added as input with shape [1], except for the first request
	//@@         in the batch. For the first request in the batch, the input
	//@@         will have shape [2] where the first element is value 0.
	//@@
	BatchInput_BATCH_ACCUMULATED_ELEMENT_COUNT_WITH_ZERO BatchInput_Kind = 2
	//@@      .. cpp:enumerator:: Kind::BATCH_MAX_ELEMENT_COUNT_AS_SHAPE = 3
	//@@
	//@@         Among the requests in the batch, the max element count of the
	//@@         'source_input' will be added as input with shape
	//@@         [max_element_count] for the first request in the batch.
	//@@         For other requests, such input will be with shape [0].
	//@@         The data of the tensor will be uninitialized.
	//@@
	BatchInput_BATCH_MAX_ELEMENT_COUNT_AS_SHAPE BatchInput_Kind = 3
)

func (BatchInput_Kind) Descriptor 

func (BatchInput_Kind) Descriptor() protoreflect.EnumDescriptor

func (BatchInput_Kind) Enum 

func (x BatchInput_Kind) Enum() *BatchInput_Kind

func (BatchInput_Kind) EnumDescriptor deprecated 

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

Deprecated: Use BatchInput_Kind.Descriptor instead.

func (BatchInput_Kind) Number 

func (x BatchInput_Kind) Number() protoreflect.EnumNumber

func (BatchInput_Kind) String 

func (x BatchInput_Kind) String() string

func (BatchInput_Kind) Type 

func (BatchInput_Kind) Type() protoreflect.EnumType

type BatchOutput 

type BatchOutput struct {

	//@@  .. cpp:var:: string target_name (repeated)
	//@@
	//@@     The name of the outputs to be produced by this batch output
	//@@     specification.
	//@@
	TargetName []string `protobuf:"bytes,1,rep,name=target_name,json=targetName,proto3" json:"target_name,omitempty"`
	//@@  .. cpp:var:: Kind kind
	//@@
	//@@     The kind of this batch output.
	//@@
	Kind BatchOutput_Kind `protobuf:"varint,2,opt,name=kind,proto3,enum=inference.BatchOutput_Kind" json:"kind,omitempty"`
	//@@  .. cpp:var:: string source_input (repeated)
	//@@
	//@@     The backend derives each batch output from one or more inputs.
	//@@     'source_input' gives the names of those inputs.
	//@@
	SourceInput []string `protobuf:"bytes,3,rep,name=source_input,json=sourceInput,proto3" json:"source_input,omitempty"`
	// contains filtered or unexported fields
}

@@.. cpp:var:: message BatchOutput @@ @@ A batch output is an output produced by the model that must be handled @@ differently by the backend based on all the requests in a batch. @@

func (*BatchOutput) Descriptor deprecated 

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

Deprecated: Use BatchOutput.ProtoReflect.Descriptor instead.

func (*BatchOutput) GetKind 

func (x *BatchOutput) GetKind() BatchOutput_Kind

func (*BatchOutput) GetSourceInput 

func (x *BatchOutput) GetSourceInput() []string

func (*BatchOutput) GetTargetName 

func (x *BatchOutput) GetTargetName() []string

func (*BatchOutput) ProtoMessage 

func (*BatchOutput) ProtoMessage()

func (*BatchOutput) ProtoReflect 

func (x *BatchOutput) ProtoReflect() protoreflect.Message

func (*BatchOutput) Reset 

func (x *BatchOutput) Reset()

func (*BatchOutput) String 

func (x *BatchOutput) String() string

type BatchOutput_Kind 

type BatchOutput_Kind int32

@@ @@ .. cpp:enum:: Kind @@ @@ The kind of the batch output. @@ 

const (
	//@@    .. cpp:enumerator:: Kind::BATCH_SCATTER_WITH_INPUT_SHAPE = 0
	//@@
	//@@       The output should be scattered according to the shape of
	//@@       'source_input'. The dynamic dimension of the output will
	//@@       be set to the value of the same dimension in the input.
	//@@
	BatchOutput_BATCH_SCATTER_WITH_INPUT_SHAPE BatchOutput_Kind = 0
)

func (BatchOutput_Kind) Descriptor 

func (BatchOutput_Kind) Descriptor() protoreflect.EnumDescriptor

func (BatchOutput_Kind) Enum 

func (x BatchOutput_Kind) Enum() *BatchOutput_Kind

func (BatchOutput_Kind) EnumDescriptor deprecated 

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

Deprecated: Use BatchOutput_Kind.Descriptor instead.

func (BatchOutput_Kind) Number 

func (x BatchOutput_Kind) Number() protoreflect.EnumNumber

func (BatchOutput_Kind) String 

func (x BatchOutput_Kind) String() string

func (BatchOutput_Kind) Type 

func (BatchOutput_Kind) Type() protoreflect.EnumType

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) Descriptor 

func (DataType) Descriptor() protoreflect.EnumDescriptor

func (DataType) Enum 

func (x DataType) Enum() *DataType

func (DataType) EnumDescriptor deprecated 

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

Deprecated: Use DataType.Descriptor instead.

func (DataType) Number 

func (x DataType) Number() protoreflect.EnumNumber

func (DataType) String 

func (x DataType) String() string

func (DataType) Type 

func (DataType) Type() protoreflect.EnumType

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", "onnxruntime_onnx",
	//@@     "pytorch_libtorch".
	//@@
	Platform string `protobuf:"bytes,2,opt,name=platform,proto3" json:"platform,omitempty"`
	//@@  .. cpp:var:: string backend
	//@@
	//@@     The backend used by the model.
	//@@
	Backend string `protobuf:"bytes,17,opt,name=backend,proto3" json:"backend,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:: BatchInput batch_input (repeated)
	//@@
	//@@     The model input(s) that the server should use to communicate
	//@@     batch related values to the model.
	//@@
	BatchInput []*BatchInput `protobuf:"bytes,20,rep,name=batch_input,json=batchInput,proto3" json:"batch_input,omitempty"`
	//@@  .. cpp:var:: BatchOutput batch_output (repeated)
	//@@
	//@@     The outputs produced by the model that requires special handling
	//@@     by the model backend.
	//@@
	BatchOutput []*BatchOutput `protobuf:"bytes,21,rep,name=batch_output,json=batchOutput,proto3" json:"batch_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 assignable 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_filenames`. If not specified the default name
	//@@     is 'model.graphdef', 'model.savedmodel', 'model.plan' or
	//@@     'model.pt' 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.
	//@@
	Parameters map[string]*ModelParameter `` /* 162-byte string literal not displayed */
	//@@  .. cpp:var:: ModelWarmup model_warmup (repeated)
	//@@
	//@@     Warmup setting of this model. If specified, all instances
	//@@     will be run with the request samples in sequence before
	//@@     serving the model.
	//@@     This field can only be specified if the model is not an ensemble
	//@@     model.
	//@@
	ModelWarmup []*ModelWarmup `protobuf:"bytes,16,rep,name=model_warmup,json=modelWarmup,proto3" json:"model_warmup,omitempty"`
	//@@  .. cpp:var:: ModelOperations model_operations
	//@@
	//@@     Optional metadata of the libraries providing custom operations for
	//@@     this model.
	//@@
	ModelOperations *ModelOperations `protobuf:"bytes,18,opt,name=model_operations,json=modelOperations,proto3" json:"model_operations,omitempty"`
	//@@  .. cpp:var:: ModelTransactionPolicy model_transaction_policy
	//@@
	//@@     Optional specification that describes the nature of transactions
	//@@     to be expected from the model.
	//@@
	ModelTransactionPolicy *ModelTransactionPolicy `` /* 130-byte string literal not displayed */
	//@@  .. cpp:var:: ModelRepositoryAgents model_repository_agents
	//@@
	//@@     Optional specification of the agent(s) that should be invoked
	//@@     with repository actions are performed for this model.
	//@@
	ModelRepositoryAgents *ModelRepositoryAgents `` /* 127-byte string literal not displayed */
	//@@  .. cpp:var:: ModelResponseCache response_cache
	//@@
	//@@     Optional setting for utilizing the response cache for this
	//@@     model.
	//@@
	ResponseCache *ModelResponseCache `protobuf:"bytes,24,opt,name=response_cache,json=responseCache,proto3" json:"response_cache,omitempty"`
	// contains filtered or unexported fields
}

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

func (*ModelConfig) Descriptor deprecated 

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

Deprecated: Use ModelConfig.ProtoReflect.Descriptor instead.

func (*ModelConfig) GetBackend 

func (x *ModelConfig) GetBackend() string

func (*ModelConfig) GetBatchInput 

func (x *ModelConfig) GetBatchInput() []*BatchInput

func (*ModelConfig) GetBatchOutput 

func (x *ModelConfig) GetBatchOutput() []*BatchOutput

func (*ModelConfig) GetCcModelFilenames 

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

func (*ModelConfig) GetDefaultModelFilename 

func (x *ModelConfig) GetDefaultModelFilename() string

func (*ModelConfig) GetDynamicBatching 

func (x *ModelConfig) GetDynamicBatching() *ModelDynamicBatching

func (*ModelConfig) GetEnsembleScheduling 

func (x *ModelConfig) GetEnsembleScheduling() *ModelEnsembling

func (*ModelConfig) GetInput 

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

func (*ModelConfig) GetInstanceGroup 

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

func (*ModelConfig) GetMaxBatchSize 

func (x *ModelConfig) GetMaxBatchSize() int32

func (*ModelConfig) GetMetricTags 

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

func (*ModelConfig) GetModelOperations 

func (x *ModelConfig) GetModelOperations() *ModelOperations

func (*ModelConfig) GetModelRepositoryAgents 

func (x *ModelConfig) GetModelRepositoryAgents() *ModelRepositoryAgents

func (*ModelConfig) GetModelTransactionPolicy 

func (x *ModelConfig) GetModelTransactionPolicy() *ModelTransactionPolicy

func (*ModelConfig) GetModelWarmup 

func (x *ModelConfig) GetModelWarmup() []*ModelWarmup

func (*ModelConfig) GetName 

func (x *ModelConfig) GetName() string

func (*ModelConfig) GetOptimization 

func (x *ModelConfig) GetOptimization() *ModelOptimizationPolicy

func (*ModelConfig) GetOutput 

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

func (*ModelConfig) GetParameters 

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

func (*ModelConfig) GetPlatform 

func (x *ModelConfig) GetPlatform() string

func (*ModelConfig) GetResponseCache 

func (x *ModelConfig) GetResponseCache() *ModelResponseCache

func (*ModelConfig) GetSchedulingChoice 

func (m *ModelConfig) GetSchedulingChoice() isModelConfig_SchedulingChoice

func (*ModelConfig) GetSequenceBatching 

func (x *ModelConfig) GetSequenceBatching() *ModelSequenceBatching

func (*ModelConfig) GetVersionPolicy 

func (x *ModelConfig) GetVersionPolicy() *ModelVersionPolicy

func (*ModelConfig) ProtoMessage 

func (*ModelConfig) ProtoMessage()

func (*ModelConfig) ProtoReflect 

func (x *ModelConfig) ProtoReflect() protoreflect.Message

func (*ModelConfig) Reset 

func (x *ModelConfig) Reset()

func (*ModelConfig) String 

func (x *ModelConfig) String() string

type ModelConfig_DynamicBatching 

type ModelConfig_DynamicBatching struct {
	//@@    .. cpp:var:: ModelDynamicBatching dynamic_batching
	//@@
	//@@       If specified, enables the dynamic-batching scheduling
	//@@       policy. With dynamic-batching the scheduler may group
	//@@       together independent requests into a single batch to
	//@@       improve inference throughput.
	//@@
	DynamicBatching *ModelDynamicBatching `protobuf:"bytes,11,opt,name=dynamic_batching,json=dynamicBatching,proto3,oneof"`
}

type ModelConfig_EnsembleScheduling 

type ModelConfig_EnsembleScheduling struct {
	//@@    .. cpp:var:: ModelEnsembling ensemble_scheduling
	//@@
	//@@       If specified, enables the model-ensembling scheduling
	//@@       policy. With model-ensembling, inference requests
	//@@       will be processed according to the specification, such as an
	//@@       execution sequence of models. The input specified in this model
	//@@       config will be the input for the ensemble, and the output
	//@@       specified will be the output of the ensemble.
	//@@
	EnsembleScheduling *ModelEnsembling `protobuf:"bytes,15,opt,name=ensemble_scheduling,json=ensembleScheduling,proto3,oneof"`
}

type ModelConfig_SequenceBatching 

type ModelConfig_SequenceBatching struct {
	//@@    .. cpp:var:: ModelSequenceBatching sequence_batching
	//@@
	//@@       If specified, enables the sequence-batching scheduling
	//@@       policy. With sequence-batching, inference requests
	//@@       with the same correlation ID are routed to the same
	//@@       model instance. Multiple sequences of inference requests
	//@@       may be batched together into a single batch to
	//@@       improve inference throughput.
	//@@
	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 */
	//@@  .. cpp:var:: bool preserve_ordering
	//@@
	//@@     Should the dynamic batcher preserve the ordering of responses to
	//@@     match the order of requests received by the scheduler. Default is
	//@@     false. If true, the responses will be returned in the same order as
	//@@     the order of requests sent to the scheduler. If false, the responses
	//@@     may be returned in arbitrary order. This option is specifically
	//@@     needed when a sequence of related inference requests (i.e. inference
	//@@     requests with the same correlation ID) are sent to the dynamic
	//@@     batcher to ensure that the sequence responses are in the correct
	//@@     order.
	//@@
	PreserveOrdering bool `protobuf:"varint,3,opt,name=preserve_ordering,json=preserveOrdering,proto3" json:"preserve_ordering,omitempty"`
	//@@  .. cpp:var:: uint32 priority_levels
	//@@
	//@@     The number of priority levels to be enabled for the model,
	//@@     the priority level starts from 1 and 1 is the highest priority.
	//@@     Requests are handled in priority order with all priority 1 requests
	//@@     processed before priority 2, all priority 2 requests processed before
	//@@     priority 3, etc. Requests with the same priority level will be
	//@@     handled in the order that they are received.
	//@@
	PriorityLevels uint32 `protobuf:"varint,4,opt,name=priority_levels,json=priorityLevels,proto3" json:"priority_levels,omitempty"`
	//@@  .. cpp:var:: uint32 default_priority_level
	//@@
	//@@     The priority level used for requests that don't specify their
	//@@     priority. The value must be in the range [ 1, 'priority_levels' ].
	//@@
	DefaultPriorityLevel uint32 `protobuf:"varint,5,opt,name=default_priority_level,json=defaultPriorityLevel,proto3" json:"default_priority_level,omitempty"`
	//@@  .. cpp:var:: ModelQueuePolicy default_queue_policy
	//@@
	//@@     The default queue policy used for requests that don't require
	//@@     priority handling and requests that specify priority levels where
	//@@     there is no specific policy given. If not specified, a policy with
	//@@     default field values will be used.
	//@@
	DefaultQueuePolicy *ModelQueuePolicy `protobuf:"bytes,6,opt,name=default_queue_policy,json=defaultQueuePolicy,proto3" json:"default_queue_policy,omitempty"`
	//@@  .. cpp:var:: map<uint32, ModelQueuePolicy> priority_queue_policy
	//@@
	//@@     Specify the queue policy for the priority level. The default queue
	//@@     policy will be used if a priority level doesn't specify a queue
	//@@     policy.
	//@@
	PriorityQueuePolicy map[uint32]*ModelQueuePolicy `` /* 209-byte string literal not displayed */
	// contains filtered or unexported fields
}

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

func (*ModelDynamicBatching) Descriptor deprecated 

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

Deprecated: Use ModelDynamicBatching.ProtoReflect.Descriptor instead.

func (*ModelDynamicBatching) GetDefaultPriorityLevel 

func (x *ModelDynamicBatching) GetDefaultPriorityLevel() uint32

func (*ModelDynamicBatching) GetDefaultQueuePolicy 

func (x *ModelDynamicBatching) GetDefaultQueuePolicy() *ModelQueuePolicy

func (*ModelDynamicBatching) GetMaxQueueDelayMicroseconds 

func (x *ModelDynamicBatching) GetMaxQueueDelayMicroseconds() uint64

func (*ModelDynamicBatching) GetPreferredBatchSize 

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

func (*ModelDynamicBatching) GetPreserveOrdering 

func (x *ModelDynamicBatching) GetPreserveOrdering() bool

func (*ModelDynamicBatching) GetPriorityLevels 

func (x *ModelDynamicBatching) GetPriorityLevels() uint32

func (*ModelDynamicBatching) GetPriorityQueuePolicy 

func (x *ModelDynamicBatching) GetPriorityQueuePolicy() map[uint32]*ModelQueuePolicy

func (*ModelDynamicBatching) ProtoMessage 

func (*ModelDynamicBatching) ProtoMessage()

func (*ModelDynamicBatching) ProtoReflect 

func (x *ModelDynamicBatching) ProtoReflect() protoreflect.Message

func (*ModelDynamicBatching) Reset 

func (x *ModelDynamicBatching) Reset()

func (*ModelDynamicBatching) String 

func (x *ModelDynamicBatching) String() string

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"`
	// contains filtered or unexported fields
}

@@ @@.. 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 deprecated 

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

Deprecated: Use ModelEnsembling.ProtoReflect.Descriptor instead.

func (*ModelEnsembling) GetStep 

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

func (*ModelEnsembling) ProtoMessage 

func (*ModelEnsembling) ProtoMessage()

func (*ModelEnsembling) ProtoReflect 

func (x *ModelEnsembling) ProtoReflect() protoreflect.Message

func (*ModelEnsembling) Reset 

func (x *ModelEnsembling) Reset()

func (*ModelEnsembling) String 

func (x *ModelEnsembling) String() string

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 */
	// contains filtered or unexported fields
}

@@ .. 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 deprecated 

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

Deprecated: Use ModelEnsembling_Step.ProtoReflect.Descriptor instead.

func (*ModelEnsembling_Step) GetInputMap 

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

func (*ModelEnsembling_Step) GetModelName 

func (x *ModelEnsembling_Step) GetModelName() string

func (*ModelEnsembling_Step) GetModelVersion 

func (x *ModelEnsembling_Step) GetModelVersion() int64

func (*ModelEnsembling_Step) GetOutputMap 

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

func (*ModelEnsembling_Step) ProtoMessage 

func (*ModelEnsembling_Step) ProtoMessage()

func (*ModelEnsembling_Step) ProtoReflect 

func (x *ModelEnsembling_Step) ProtoReflect() protoreflect.Message

func (*ModelEnsembling_Step) Reset 

func (x *ModelEnsembling_Step) Reset()

func (*ModelEnsembling_Step) String 

func (x *ModelEnsembling_Step) String() string

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=inference.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=inference.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"`
	//@@  .. cpp:var:: bool is_shape_tensor
	//@@
	//@@     Whether or not the input is a shape tensor to the model. This field
	//@@     is currently supported only for the TensorRT model. An error will be
	//@@     generated if this specification does not comply with underlying
	//@@     model.
	//@@
	IsShapeTensor bool `protobuf:"varint,6,opt,name=is_shape_tensor,json=isShapeTensor,proto3" json:"is_shape_tensor,omitempty"`
	//@@  .. cpp:var:: bool allow_ragged_batch
	//@@
	//@@     Whether or not the input is allowed to be "ragged" in a dynamically
	//@@     created batch. Default is false indicating that two requests will
	//@@     only be batched if this tensor has the same shape in both requests.
	//@@     True indicates that two requests can be batched even if this tensor
	//@@     has a different shape in each request.
	//@@
	AllowRaggedBatch bool `protobuf:"varint,7,opt,name=allow_ragged_batch,json=allowRaggedBatch,proto3" json:"allow_ragged_batch,omitempty"`
	//@@  .. cpp:var:: bool optional
	//@@
	//@@     Whether or not the input is optional for the model execution.
	//@@     If true, the input is not required in the inference request.
	//@@     Default value is false.
	//@@
	Optional bool `protobuf:"varint,8,opt,name=optional,proto3" json:"optional,omitempty"`
	// contains filtered or unexported fields
}

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

func (*ModelInput) Descriptor deprecated 

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

Deprecated: Use ModelInput.ProtoReflect.Descriptor instead.

func (*ModelInput) GetAllowRaggedBatch 

func (x *ModelInput) GetAllowRaggedBatch() bool

func (*ModelInput) GetDataType 

func (x *ModelInput) GetDataType() DataType

func (*ModelInput) GetDims 

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

func (*ModelInput) GetFormat 

func (x *ModelInput) GetFormat() ModelInput_Format

func (*ModelInput) GetIsShapeTensor 

func (x *ModelInput) GetIsShapeTensor() bool

func (*ModelInput) GetName 

func (x *ModelInput) GetName() string

func (*ModelInput) GetOptional 

func (x *ModelInput) GetOptional() bool

func (*ModelInput) GetReshape 

func (x *ModelInput) GetReshape() *ModelTensorReshape

func (*ModelInput) ProtoMessage 

func (*ModelInput) ProtoMessage()

func (*ModelInput) ProtoReflect 

func (x *ModelInput) ProtoReflect() protoreflect.Message

func (*ModelInput) Reset 

func (x *ModelInput) Reset()

func (*ModelInput) String 

func (x *ModelInput) String() string

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) Descriptor 

func (ModelInput_Format) Descriptor() protoreflect.EnumDescriptor

func (ModelInput_Format) Enum 

func (x ModelInput_Format) Enum() *ModelInput_Format

func (ModelInput_Format) EnumDescriptor deprecated 

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

Deprecated: Use ModelInput_Format.Descriptor instead.

func (ModelInput_Format) Number 

func (x ModelInput_Format) Number() protoreflect.EnumNumber

func (ModelInput_Format) String 

func (x ModelInput_Format) String() string

func (ModelInput_Format) Type 

func (ModelInput_Format) Type() protoreflect.EnumType

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 or KIND_MODEL only 'count' is valid
	//@@     and 'gpu' cannot be specified.
	//@@
	Kind ModelInstanceGroup_Kind `protobuf:"varint,4,opt,name=kind,proto3,enum=inference.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:: ModelRateLimiter rate_limiter
	//@@
	//@@     The rate limiter specific settings to be associated with this
	//@@     instance group. Optional, if not specified no rate limiting
	//@@     will be applied to this instance group.
	//@@
	RateLimiter *ModelRateLimiter `protobuf:"bytes,6,opt,name=rate_limiter,json=rateLimiter,proto3" json:"rate_limiter,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"`
	//@@  .. cpp:var:: SecondaryDevice secondary_devices (repeated)
	//@@
	//@@     Secondary devices that are required by instances specified by this
	//@@     instance group. Optional.
	//@@
	SecondaryDevices []*ModelInstanceGroup_SecondaryDevice `protobuf:"bytes,8,rep,name=secondary_devices,json=secondaryDevices,proto3" json:"secondary_devices,omitempty"`
	//@@  .. cpp:var:: string profile (repeated)
	//@@
	//@@     For TensorRT models containing multiple optimization profile, this
	//@@     parameter specifies a set of optimization profiles available to this
	//@@     instance group. The inference server will choose the optimal profile
	//@@     based on the shapes of the input tensors. This field should lie
	//@@     between 0 and <TotalNumberOfOptimizationProfilesInPlanModel> - 1
	//@@     and be specified only for TensorRT backend, otherwise an error will
	//@@     be generated. If not specified, the server will select the first
	//@@     optimization profile by default.
	//@@
	Profile []string `protobuf:"bytes,5,rep,name=profile,proto3" json:"profile,omitempty"`
	//@@  .. cpp:var:: bool passive
	//@@
	//@@     Whether the instances within this instance group will be accepting
	//@@     inference requests from the scheduler. If true, the instances will
	//@@     not be added to the scheduler. Default value is false.
	//@@
	Passive bool `protobuf:"varint,7,opt,name=passive,proto3" json:"passive,omitempty"`
	//@@  .. cpp:var:: string host_policy
	//@@
	//@@     The host policy name that the instance to be associated with.
	//@@     The default value is set to reflect the device kind of the instance,
	//@@     for instance, KIND_CPU is "cpu", KIND_MODEL is "model" and
	//@@     KIND_GPU is "gpu_<gpu_id>".
	//@@
	HostPolicy string `protobuf:"bytes,9,opt,name=host_policy,json=hostPolicy,proto3" json:"host_policy,omitempty"`
	// contains filtered or unexported fields
}

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

func (*ModelInstanceGroup) Descriptor deprecated 

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

Deprecated: Use ModelInstanceGroup.ProtoReflect.Descriptor instead.

func (*ModelInstanceGroup) GetCount 

func (x *ModelInstanceGroup) GetCount() int32

func (*ModelInstanceGroup) GetGpus 

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

func (*ModelInstanceGroup) GetHostPolicy 

func (x *ModelInstanceGroup) GetHostPolicy() string

func (*ModelInstanceGroup) GetKind 

func (x *ModelInstanceGroup) GetKind() ModelInstanceGroup_Kind

func (*ModelInstanceGroup) GetName 

func (x *ModelInstanceGroup) GetName() string

func (*ModelInstanceGroup) GetPassive 

func (x *ModelInstanceGroup) GetPassive() bool

func (*ModelInstanceGroup) GetProfile 

func (x *ModelInstanceGroup) GetProfile() []string

func (*ModelInstanceGroup) GetRateLimiter 

func (x *ModelInstanceGroup) GetRateLimiter() *ModelRateLimiter

func (*ModelInstanceGroup) GetSecondaryDevices 

func (x *ModelInstanceGroup) GetSecondaryDevices() []*ModelInstanceGroup_SecondaryDevice

func (*ModelInstanceGroup) ProtoMessage 

func (*ModelInstanceGroup) ProtoMessage()

func (*ModelInstanceGroup) ProtoReflect 

func (x *ModelInstanceGroup) ProtoReflect() protoreflect.Message

func (*ModelInstanceGroup) Reset 

func (x *ModelInstanceGroup) Reset()

func (*ModelInstanceGroup) String 

func (x *ModelInstanceGroup) String() string

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
	//@@    .. cpp:enumerator:: Kind::KIND_MODEL = 3
	//@@
	//@@       This instance group represents instances that should run on the
	//@@       CPU and/or GPU(s) as specified by the model or backend itself.
	//@@       The inference server will not override the model/backend
	//@@       settings.
	//@@
	ModelInstanceGroup_KIND_MODEL ModelInstanceGroup_Kind = 3
)

func (ModelInstanceGroup_Kind) Descriptor 

func (ModelInstanceGroup_Kind) Descriptor() protoreflect.EnumDescriptor

func (ModelInstanceGroup_Kind) Enum 

func (x ModelInstanceGroup_Kind) Enum() *ModelInstanceGroup_Kind

func (ModelInstanceGroup_Kind) EnumDescriptor deprecated 

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

Deprecated: Use ModelInstanceGroup_Kind.Descriptor instead.

func (ModelInstanceGroup_Kind) Number 

func (x ModelInstanceGroup_Kind) Number() protoreflect.EnumNumber

func (ModelInstanceGroup_Kind) String 

func (x ModelInstanceGroup_Kind) String() string

func (ModelInstanceGroup_Kind) Type 

func (ModelInstanceGroup_Kind) Type() protoreflect.EnumType

type ModelInstanceGroup_SecondaryDevice 

type ModelInstanceGroup_SecondaryDevice struct {

	//@@  .. cpp:var:: SecondaryDeviceKind kind
	//@@
	//@@     The secondary device kind.
	//@@
	Kind ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind `` /* 132-byte string literal not displayed */
	//@@  .. cpp:var:: int64 device_id
	//@@
	//@@     Identifier for the secondary device.
	//@@
	DeviceId int64 `protobuf:"varint,2,opt,name=device_id,json=deviceId,proto3" json:"device_id,omitempty"`
	// contains filtered or unexported fields
}

@@ @@ .. cpp:var:: message SecondaryDevice @@ @@ A secondary device required for a model instance. @@

func (*ModelInstanceGroup_SecondaryDevice) Descriptor deprecated 

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

Deprecated: Use ModelInstanceGroup_SecondaryDevice.ProtoReflect.Descriptor instead.

func (*ModelInstanceGroup_SecondaryDevice) GetDeviceId 

func (x *ModelInstanceGroup_SecondaryDevice) GetDeviceId() int64

func (*ModelInstanceGroup_SecondaryDevice) GetKind 

func (x *ModelInstanceGroup_SecondaryDevice) GetKind() ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind

func (*ModelInstanceGroup_SecondaryDevice) ProtoMessage 

func (*ModelInstanceGroup_SecondaryDevice) ProtoMessage()

func (*ModelInstanceGroup_SecondaryDevice) ProtoReflect 

func (x *ModelInstanceGroup_SecondaryDevice) ProtoReflect() protoreflect.Message

func (*ModelInstanceGroup_SecondaryDevice) Reset 

func (x *ModelInstanceGroup_SecondaryDevice) Reset()

func (*ModelInstanceGroup_SecondaryDevice) String 

func (x *ModelInstanceGroup_SecondaryDevice) String() string

type ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind 

type ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind int32

@@ @@ .. cpp:enum:: SecondaryDeviceKind @@ @@ The kind of the secondary device. @@ 

const (
	//@@    .. cpp:enumerator:: SecondaryDeviceKind::KIND_NVDLA = 0
	//@@
	//@@       An NVDLA core. http://nvdla.org
	//@@       Currently KIND_NVDLA is only supported by the TensorRT backend.
	//@@
	ModelInstanceGroup_SecondaryDevice_KIND_NVDLA ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind = 0
)

func (ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind) Descriptor 

func (ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind) Descriptor() protoreflect.EnumDescriptor

func (ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind) Enum 

func (x ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind) Enum() *ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind

func (ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind) EnumDescriptor deprecated 

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

Deprecated: Use ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind.Descriptor instead.

func (ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind) Number 

func (x ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind) Number() protoreflect.EnumNumber

func (ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind) String 

func (x ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind) String() string

func (ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind) Type 

func (ModelInstanceGroup_SecondaryDevice_SecondaryDeviceKind) Type() protoreflect.EnumType

type ModelOperations 

type ModelOperations struct {

	//@@  .. cpp:var:: string op_library_filename (repeated)
	//@@
	//@@     Optional paths of the libraries providing custom operations for
	//@@     this model. Valid only for ONNX models.
	//@@
	OpLibraryFilename []string `protobuf:"bytes,1,rep,name=op_library_filename,json=opLibraryFilename,proto3" json:"op_library_filename,omitempty"`
	// contains filtered or unexported fields
}

@@ @@ .. cpp:var:: message ModelOperations @@ @@ The metadata of libraries providing custom operations for this model. @@

func (*ModelOperations) Descriptor deprecated 

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

Deprecated: Use ModelOperations.ProtoReflect.Descriptor instead.

func (*ModelOperations) GetOpLibraryFilename 

func (x *ModelOperations) GetOpLibraryFilename() []string

func (*ModelOperations) ProtoMessage 

func (*ModelOperations) ProtoMessage()

func (*ModelOperations) ProtoReflect 

func (x *ModelOperations) ProtoReflect() protoreflect.Message

func (*ModelOperations) Reset 

func (x *ModelOperations) Reset()

func (*ModelOperations) String 

func (x *ModelOperations) 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 `protobuf:"varint,2,opt,name=priority,proto3,enum=inference.ModelOptimizationPolicy_ModelPriority" json:"priority,omitempty"`
	//@@  .. cpp:var:: Cuda cuda
	//@@
	//@@     CUDA-specific optimization settings. Optional.
	//@@
	Cuda *ModelOptimizationPolicy_Cuda `protobuf:"bytes,3,opt,name=cuda,proto3" json:"cuda,omitempty"`
	//@@  .. cpp:var:: ExecutionAccelerators execution_accelerators
	//@@
	//@@     The accelerators used for the model. Optional.
	//@@
	ExecutionAccelerators *ModelOptimizationPolicy_ExecutionAccelerators `protobuf:"bytes,4,opt,name=execution_accelerators,json=executionAccelerators,proto3" json:"execution_accelerators,omitempty"`
	//@@  .. cpp:var:: PinnedMemoryBuffer input_pinned_memory
	//@@
	//@@     Use pinned memory buffer when the data transfer for inputs
	//@@     is between GPU memory and non-pinned system memory.
	//@@     Default is true.
	//@@
	InputPinnedMemory *ModelOptimizationPolicy_PinnedMemoryBuffer `protobuf:"bytes,5,opt,name=input_pinned_memory,json=inputPinnedMemory,proto3" json:"input_pinned_memory,omitempty"`
	//@@  .. cpp:var:: PinnedMemoryBuffer output_pinned_memory
	//@@
	//@@     Use pinned memory buffer when the data transfer for outputs
	//@@     is between GPU memory and non-pinned system memory.
	//@@     Default is true.
	//@@
	OutputPinnedMemory *ModelOptimizationPolicy_PinnedMemoryBuffer `protobuf:"bytes,6,opt,name=output_pinned_memory,json=outputPinnedMemory,proto3" json:"output_pinned_memory,omitempty"`
	//@@  .. cpp:var:: uint32 gather_kernel_buffer_threshold
	//@@
	//@@     The backend may use a gather kernel to gather input data if the
	//@@     device has direct access to the source buffer and the destination
	//@@     buffer. In such case, the gather kernel will be used only if the
	//@@     number of buffers to be gathered is greater or equal to
	//@@     the specifed value. If 0, the gather kernel will be disabled.
	//@@     Default value is 0.
	//@@     Currently only recognized by TensorRT backend.
	//@@
	GatherKernelBufferThreshold uint32 `` /* 147-byte string literal not displayed */
	//@@  .. cpp:var:: bool eager_batching
	//@@
	//@@     Start preparing the next batch before the model instance is ready
	//@@     for the next inference. This option can be used to overlap the
	//@@     batch preparation with model execution, with the trade-off that
	//@@     the next batch might be smaller than what it could have been.
	//@@     Default value is false.
	//@@     Currently only recognized by TensorRT backend.
	//@@
	EagerBatching bool `protobuf:"varint,8,opt,name=eager_batching,json=eagerBatching,proto3" json:"eager_batching,omitempty"`
	// contains filtered or unexported fields
}

@@ @@.. 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 deprecated 

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

Deprecated: Use ModelOptimizationPolicy.ProtoReflect.Descriptor instead.

func (*ModelOptimizationPolicy) GetCuda 

func (x *ModelOptimizationPolicy) GetCuda() *ModelOptimizationPolicy_Cuda

func (*ModelOptimizationPolicy) GetEagerBatching 

func (x *ModelOptimizationPolicy) GetEagerBatching() bool

func (*ModelOptimizationPolicy) GetExecutionAccelerators 

func (x *ModelOptimizationPolicy) GetExecutionAccelerators() *ModelOptimizationPolicy_ExecutionAccelerators

func (*ModelOptimizationPolicy) GetGatherKernelBufferThreshold 

func (x *ModelOptimizationPolicy) GetGatherKernelBufferThreshold() uint32

func (*ModelOptimizationPolicy) GetGraph 

func (x *ModelOptimizationPolicy) GetGraph() *ModelOptimizationPolicy_Graph

func (*ModelOptimizationPolicy) GetInputPinnedMemory 

func (x *ModelOptimizationPolicy) GetInputPinnedMemory() *ModelOptimizationPolicy_PinnedMemoryBuffer

func (*ModelOptimizationPolicy) GetOutputPinnedMemory 

func (x *ModelOptimizationPolicy) GetOutputPinnedMemory() *ModelOptimizationPolicy_PinnedMemoryBuffer

func (*ModelOptimizationPolicy) GetPriority 

func (x *ModelOptimizationPolicy) GetPriority() ModelOptimizationPolicy_ModelPriority

func (*ModelOptimizationPolicy) ProtoMessage 

func (*ModelOptimizationPolicy) ProtoMessage()

func (*ModelOptimizationPolicy) ProtoReflect 

func (x *ModelOptimizationPolicy) ProtoReflect() protoreflect.Message

func (*ModelOptimizationPolicy) Reset 

func (x *ModelOptimizationPolicy) Reset()

func (*ModelOptimizationPolicy) String 

func (x *ModelOptimizationPolicy) String() string

type ModelOptimizationPolicy_Cuda 

type ModelOptimizationPolicy_Cuda struct {

	//@@    .. cpp:var:: bool graphs
	//@@
	//@@       Use CUDA graphs API to capture model operations and execute
	//@@       them more efficiently. Default value is false.
	//@@       Currently only recognized by TensorRT backend.
	//@@
	Graphs bool `protobuf:"varint,1,opt,name=graphs,proto3" json:"graphs,omitempty"`
	//@@    .. cpp:var:: bool busy_wait_events
	//@@
	//@@       Use busy-waiting to synchronize CUDA events to achieve minimum
	//@@       latency from event complete to host thread to be notified, with
	//@@       the cost of high CPU load. Default value is false.
	//@@       Currently only recognized by TensorRT backend.
	//@@
	BusyWaitEvents bool `protobuf:"varint,2,opt,name=busy_wait_events,json=busyWaitEvents,proto3" json:"busy_wait_events,omitempty"`
	//@@    .. cpp:var:: GraphSpec graph_spec (repeated)
	//@@
	//@@       Specification of the CUDA graph to be captured. If not specified
	//@@       and 'graphs' is true, the default CUDA graphs will be captured
	//@@       based on model settings.
	//@@       Currently only recognized by TensorRT backend.
	//@@
	GraphSpec []*ModelOptimizationPolicy_Cuda_GraphSpec `protobuf:"bytes,3,rep,name=graph_spec,json=graphSpec,proto3" json:"graph_spec,omitempty"`
	//@@    .. cpp:var:: bool output_copy_stream
	//@@
	//@@       Uses a CUDA stream separate from the inference stream to copy the
	//@@       output to host. However, be aware that setting this option to
	//@@       true will lead to an increase in the memory consumption of the
	//@@       model as Triton will allocate twice as much GPU memory for its
	//@@       I/O tensor buffers. Default value is false.
	//@@       Currently only recognized by TensorRT backend.
	//@@
	OutputCopyStream bool `protobuf:"varint,4,opt,name=output_copy_stream,json=outputCopyStream,proto3" json:"output_copy_stream,omitempty"`
	// contains filtered or unexported fields
}

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

func (*ModelOptimizationPolicy_Cuda) Descriptor deprecated 

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

Deprecated: Use ModelOptimizationPolicy_Cuda.ProtoReflect.Descriptor instead.

func (*ModelOptimizationPolicy_Cuda) GetBusyWaitEvents 

func (x *ModelOptimizationPolicy_Cuda) GetBusyWaitEvents() bool

func (*ModelOptimizationPolicy_Cuda) GetGraphSpec 

func (x *ModelOptimizationPolicy_Cuda) GetGraphSpec() []*ModelOptimizationPolicy_Cuda_GraphSpec

func (*ModelOptimizationPolicy_Cuda) GetGraphs 

func (x *ModelOptimizationPolicy_Cuda) GetGraphs() bool

func (*ModelOptimizationPolicy_Cuda) GetOutputCopyStream 

func (x *ModelOptimizationPolicy_Cuda) GetOutputCopyStream() bool

func (*ModelOptimizationPolicy_Cuda) ProtoMessage 

func (*ModelOptimizationPolicy_Cuda) ProtoMessage()

func (*ModelOptimizationPolicy_Cuda) ProtoReflect 

func (x *ModelOptimizationPolicy_Cuda) ProtoReflect() protoreflect.Message

func (*ModelOptimizationPolicy_Cuda) Reset 

func (x *ModelOptimizationPolicy_Cuda) Reset()

func (*ModelOptimizationPolicy_Cuda) String 

func (x *ModelOptimizationPolicy_Cuda) String() string

type ModelOptimizationPolicy_Cuda_GraphSpec 

type ModelOptimizationPolicy_Cuda_GraphSpec struct {

	//@@      .. cpp:var:: int32 batch_size
	//@@
	//@@         The batch size of the CUDA graph. If 'max_batch_size' is 0,
	//@@         'batch_size' must be set to 0. Otherwise, 'batch_size' must
	//@@         be set to value between 1 and 'max_batch_size'.
	//@@
	BatchSize int32 `protobuf:"varint,1,opt,name=batch_size,json=batchSize,proto3" json:"batch_size,omitempty"`
	//@@      .. cpp:var:: map<string, Shape> input
	//@@
	//@@         The specification of the inputs. 'Shape' is the shape of the
	//@@         input without batching dimension.
	//@@
	Input map[string]*ModelOptimizationPolicy_Cuda_GraphSpec_Shape `` /* 151-byte string literal not displayed */
	//@@      .. cpp:var:: LowerBound graph_lower_bound
	//@@
	//@@         Specify the lower bound of the CUDA graph. Optional.
	//@@         If specified, the graph can be used for input shapes and
	//@@         batch sizes that are in closed interval between the lower
	//@@         bound specification and graph specification. For dynamic
	//@@         shape model, this allows CUDA graphs to be launched
	//@@         frequently without capturing all possible shape combinations.
	//@@         However, using graph for shape combinations different from
	//@@         the one used for capturing introduces uninitialized data for
	//@@         execution and it may distort the inference result if
	//@@         the model is sensitive to uninitialized data.
	//@@
	GraphLowerBound *ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound `protobuf:"bytes,3,opt,name=graph_lower_bound,json=graphLowerBound,proto3" json:"graph_lower_bound,omitempty"`
	// contains filtered or unexported fields
}

@@ .. cpp:var:: message GraphSpec @@ @@ Specification of the CUDA graph to be captured. @@

func (*ModelOptimizationPolicy_Cuda_GraphSpec) Descriptor deprecated 

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

Deprecated: Use ModelOptimizationPolicy_Cuda_GraphSpec.ProtoReflect.Descriptor instead.

func (*ModelOptimizationPolicy_Cuda_GraphSpec) GetBatchSize 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec) GetBatchSize() int32

func (*ModelOptimizationPolicy_Cuda_GraphSpec) GetGraphLowerBound 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec) GetGraphLowerBound() *ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound

func (*ModelOptimizationPolicy_Cuda_GraphSpec) GetInput 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec) GetInput() map[string]*ModelOptimizationPolicy_Cuda_GraphSpec_Shape

func (*ModelOptimizationPolicy_Cuda_GraphSpec) ProtoMessage 

func (*ModelOptimizationPolicy_Cuda_GraphSpec) ProtoMessage()

func (*ModelOptimizationPolicy_Cuda_GraphSpec) ProtoReflect 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec) ProtoReflect() protoreflect.Message

func (*ModelOptimizationPolicy_Cuda_GraphSpec) Reset 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec) Reset()

func (*ModelOptimizationPolicy_Cuda_GraphSpec) String 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec) String() string

type ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound 

type ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound struct {

	//@@      .. cpp:var:: int32 batch_size
	//@@
	//@@         The batch size of the CUDA graph. If 'max_batch_size' is 0,
	//@@         'batch_size' must be set to 0. Otherwise, 'batch_size' must
	//@@         be set to value between 1 and 'max_batch_size'.
	//@@
	BatchSize int32 `protobuf:"varint,1,opt,name=batch_size,json=batchSize,proto3" json:"batch_size,omitempty"`
	//@@      .. cpp:var:: map<string, Shape> input
	//@@
	//@@         The specification of the inputs. 'Shape' is the shape of
	//@@         the input without batching dimension.
	//@@
	Input map[string]*ModelOptimizationPolicy_Cuda_GraphSpec_Shape `` /* 151-byte string literal not displayed */
	// contains filtered or unexported fields
}

func (*ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound) Descriptor deprecated 

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

Deprecated: Use ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound.ProtoReflect.Descriptor instead.

func (*ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound) GetBatchSize 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound) GetBatchSize() int32

func (*ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound) GetInput 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound) GetInput() map[string]*ModelOptimizationPolicy_Cuda_GraphSpec_Shape

func (*ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound) ProtoMessage 

func (*ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound) ProtoMessage()

func (*ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound) ProtoReflect 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound) ProtoReflect() protoreflect.Message

func (*ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound) Reset 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound) Reset()

func (*ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound) String 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec_LowerBound) String() string

type ModelOptimizationPolicy_Cuda_GraphSpec_Shape 

type ModelOptimizationPolicy_Cuda_GraphSpec_Shape struct {

	//@@        .. cpp:var:: int64 dim (repeated)
	//@@
	//@@           The dimension.
	//@@
	Dim []int64 `protobuf:"varint,1,rep,packed,name=dim,proto3" json:"dim,omitempty"`
	// contains filtered or unexported fields
}

@@ .. cpp:var:: message Dims @@ @@ Specification of tensor dimension. @@

func (*ModelOptimizationPolicy_Cuda_GraphSpec_Shape) Descriptor deprecated 

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

Deprecated: Use ModelOptimizationPolicy_Cuda_GraphSpec_Shape.ProtoReflect.Descriptor instead.

func (*ModelOptimizationPolicy_Cuda_GraphSpec_Shape) GetDim 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec_Shape) GetDim() []int64

func (*ModelOptimizationPolicy_Cuda_GraphSpec_Shape) ProtoMessage 

func (*ModelOptimizationPolicy_Cuda_GraphSpec_Shape) ProtoMessage()

func (*ModelOptimizationPolicy_Cuda_GraphSpec_Shape) ProtoReflect 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec_Shape) ProtoReflect() protoreflect.Message

func (*ModelOptimizationPolicy_Cuda_GraphSpec_Shape) Reset 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec_Shape) Reset()

func (*ModelOptimizationPolicy_Cuda_GraphSpec_Shape) String 

func (x *ModelOptimizationPolicy_Cuda_GraphSpec_Shape) String() string

type ModelOptimizationPolicy_ExecutionAccelerators 

type ModelOptimizationPolicy_ExecutionAccelerators struct {

	//@@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
	//@@
	//@@       The preferred execution provider to be used if the model instance
	//@@       is deployed on GPU.
	//@@
	//@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
	//@@       and no parameters are required.
	//@@
	//@@       For TensorFlow backend, possible values are "tensorrt",
	//@@       "auto_mixed_precision", "gpu_io".
	//@@
	//@@       For "tensorrt", the following parameters can be specified:
	//@@         "precision_mode": The precision used for optimization.
	//@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
	//@@
	//@@         "max_cached_engines": The maximum number of cached TensorRT
	//@@         engines in dynamic TensorRT ops. Default value is 100.
	//@@
	//@@         "minimum_segment_size": The smallest model subgraph that will
	//@@         be considered for optimization by TensorRT. Default value is 3.
	//@@
	//@@         "max_workspace_size_bytes": The maximum GPU memory the model
	//@@         can use temporarily during execution. Default value is 1GB.
	//@@
	//@@       For "auto_mixed_precision", no parameters are required. If set,
	//@@       the model will try to use FP16 for better performance.
	//@@       This optimization can not be set with "tensorrt".
	//@@
	//@@       For "gpu_io", no parameters are required. If set, the model will
	//@@       be executed using TensorFlow Callable API to set input and output
	//@@       tensors in GPU memory if possible, which can reduce data transfer
	//@@       overhead if the model is used in ensemble. However, the Callable
	//@@       object will be created on model creation and it will request all
	//@@       outputs for every model execution, which may impact the
	//@@       performance if a request does not require all outputs. This
	//@@       optimization will only take affect if the model instance is
	//@@       created with KIND_GPU.
	//@@
	GpuExecutionAccelerator []*ModelOptimizationPolicy_ExecutionAccelerators_Accelerator `` /* 132-byte string literal not displayed */
	//@@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
	//@@
	//@@       The preferred execution provider to be used if the model instance
	//@@       is deployed on CPU.
	//@@
	//@@       For ONNX Runtime backend, possible value is "openvino" as name,
	//@@       and no parameters are required.
	//@@
	CpuExecutionAccelerator []*ModelOptimizationPolicy_ExecutionAccelerators_Accelerator `` /* 132-byte string literal not displayed */
	// contains filtered or unexported fields
}

@@ @@ .. cpp:var:: message ExecutionAccelerators @@ @@ Specify the preferred execution accelerators to be used to execute @@ the model. Currently only recognized by ONNX Runtime backend and @@ TensorFlow backend. @@ @@ For ONNX Runtime backend, it will deploy the model with the execution @@ accelerators by priority, the priority is determined based on the @@ order that they are set, i.e. the provider at the front has highest @@ priority. Overall, the priority will be in the following order: @@ <gpu_execution_accelerator> (if instance is on GPU) @@ CUDA Execution Provider (if instance is on GPU) @@ <cpu_execution_accelerator> @@ Default CPU Execution Provider @@

func (*ModelOptimizationPolicy_ExecutionAccelerators) Descriptor deprecated 

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

Deprecated: Use ModelOptimizationPolicy_ExecutionAccelerators.ProtoReflect.Descriptor instead.

func (*ModelOptimizationPolicy_ExecutionAccelerators) GetCpuExecutionAccelerator 

func (x *ModelOptimizationPolicy_ExecutionAccelerators) GetCpuExecutionAccelerator() []*ModelOptimizationPolicy_ExecutionAccelerators_Accelerator

func (*ModelOptimizationPolicy_ExecutionAccelerators) GetGpuExecutionAccelerator 

func (x *ModelOptimizationPolicy_ExecutionAccelerators) GetGpuExecutionAccelerator() []*ModelOptimizationPolicy_ExecutionAccelerators_Accelerator

func (*ModelOptimizationPolicy_ExecutionAccelerators) ProtoMessage 

func (*ModelOptimizationPolicy_ExecutionAccelerators) ProtoMessage()

func (*ModelOptimizationPolicy_ExecutionAccelerators) ProtoReflect 

func (x *ModelOptimizationPolicy_ExecutionAccelerators) ProtoReflect() protoreflect.Message

func (*ModelOptimizationPolicy_ExecutionAccelerators) Reset 

func (x *ModelOptimizationPolicy_ExecutionAccelerators) Reset()

func (*ModelOptimizationPolicy_ExecutionAccelerators) String 

func (x *ModelOptimizationPolicy_ExecutionAccelerators) String() string

type ModelOptimizationPolicy_ExecutionAccelerators_Accelerator 

type ModelOptimizationPolicy_ExecutionAccelerators_Accelerator struct {

	//@@    .. cpp:var:: string name
	//@@
	//@@       The name of the execution accelerator.
	//@@
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	//@@    .. cpp:var:: map<string, string> parameters
	//@@
	//@@       Additional paremeters used to configure the accelerator.
	//@@
	Parameters map[string]string `` /* 161-byte string literal not displayed */
	// contains filtered or unexported fields
}

@@ @@ .. cpp:var:: message Accelerator @@ @@ Specify the accelerator to be used to execute the model. @@ Accelerator with the same name may accept different parameters @@ depending on the backends. @@

func (*ModelOptimizationPolicy_ExecutionAccelerators_Accelerator) Descriptor deprecated 

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

Deprecated: Use ModelOptimizationPolicy_ExecutionAccelerators_Accelerator.ProtoReflect.Descriptor instead.

func (*ModelOptimizationPolicy_ExecutionAccelerators_Accelerator) GetName 

func (x *ModelOptimizationPolicy_ExecutionAccelerators_Accelerator) GetName() string

func (*ModelOptimizationPolicy_ExecutionAccelerators_Accelerator) GetParameters 

func (x *ModelOptimizationPolicy_ExecutionAccelerators_Accelerator) GetParameters() map[string]string

func (*ModelOptimizationPolicy_ExecutionAccelerators_Accelerator) ProtoMessage 

func (*ModelOptimizationPolicy_ExecutionAccelerators_Accelerator) ProtoMessage()

func (*ModelOptimizationPolicy_ExecutionAccelerators_Accelerator) ProtoReflect 

func (x *ModelOptimizationPolicy_ExecutionAccelerators_Accelerator) ProtoReflect() protoreflect.Message

func (*ModelOptimizationPolicy_ExecutionAccelerators_Accelerator) Reset 

func (x *ModelOptimizationPolicy_ExecutionAccelerators_Accelerator) Reset()

func (*ModelOptimizationPolicy_ExecutionAccelerators_Accelerator) String 

func (x *ModelOptimizationPolicy_ExecutionAccelerators_Accelerator) String() string

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"`
	// contains filtered or unexported fields
}

@@ @@ .. cpp:var:: message Graph @@ @@ Enable generic graph optimization of the model. If not specified @@ the framework's default level of optimization is used. Supports @@ TensorFlow graphdef and savedmodel and Onnx models. For TensorFlow @@ causes XLA to be enabled/disabled for the model. For Onnx defaults @@ to enabling all optimizations, -1 enables only basic optimizations, @@ +1 enables only basic and extended optimizations. @@

func (*ModelOptimizationPolicy_Graph) Descriptor deprecated 

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

Deprecated: Use ModelOptimizationPolicy_Graph.ProtoReflect.Descriptor instead.

func (*ModelOptimizationPolicy_Graph) GetLevel 

func (x *ModelOptimizationPolicy_Graph) GetLevel() int32

func (*ModelOptimizationPolicy_Graph) ProtoMessage 

func (*ModelOptimizationPolicy_Graph) ProtoMessage()

func (*ModelOptimizationPolicy_Graph) ProtoReflect 

func (x *ModelOptimizationPolicy_Graph) ProtoReflect() protoreflect.Message

func (*ModelOptimizationPolicy_Graph) Reset 

func (x *ModelOptimizationPolicy_Graph) Reset()

func (*ModelOptimizationPolicy_Graph) String 

func (x *ModelOptimizationPolicy_Graph) String() string

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) Descriptor 

func (ModelOptimizationPolicy_ModelPriority) Descriptor() protoreflect.EnumDescriptor

func (ModelOptimizationPolicy_ModelPriority) Enum 

func (x ModelOptimizationPolicy_ModelPriority) Enum() *ModelOptimizationPolicy_ModelPriority

func (ModelOptimizationPolicy_ModelPriority) EnumDescriptor deprecated 

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

Deprecated: Use ModelOptimizationPolicy_ModelPriority.Descriptor instead.

func (ModelOptimizationPolicy_ModelPriority) Number 

func (x ModelOptimizationPolicy_ModelPriority) Number() protoreflect.EnumNumber

func (ModelOptimizationPolicy_ModelPriority) String 

func (x ModelOptimizationPolicy_ModelPriority) String() string

func (ModelOptimizationPolicy_ModelPriority) Type 

func (ModelOptimizationPolicy_ModelPriority) Type() protoreflect.EnumType

type ModelOptimizationPolicy_PinnedMemoryBuffer 

type ModelOptimizationPolicy_PinnedMemoryBuffer struct {

	//@@    .. cpp:var:: bool enable
	//@@
	//@@       Use pinned memory buffer. Default is true.
	//@@
	Enable bool `protobuf:"varint,1,opt,name=enable,proto3" json:"enable,omitempty"`
	// contains filtered or unexported fields
}

@@ @@ .. cpp:var:: message PinnedMemoryBuffer @@ @@ Specify whether to use a pinned memory buffer when transferring data @@ between non-pinned system memory and GPU memory. Using a pinned @@ memory buffer for system from/to GPU transfers will typically provide @@ increased performance. For example, in the common use case where the @@ request provides inputs and delivers outputs via non-pinned system @@ memory, if the model instance accepts GPU IOs, the inputs will be @@ processed by two copies: from non-pinned system memory to pinned @@ memory, and from pinned memory to GPU memory. Similarly, pinned @@ memory will be used for delivering the outputs. @@

func (*ModelOptimizationPolicy_PinnedMemoryBuffer) Descriptor deprecated 

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

Deprecated: Use ModelOptimizationPolicy_PinnedMemoryBuffer.ProtoReflect.Descriptor instead.

func (*ModelOptimizationPolicy_PinnedMemoryBuffer) GetEnable 

func (x *ModelOptimizationPolicy_PinnedMemoryBuffer) GetEnable() bool

func (*ModelOptimizationPolicy_PinnedMemoryBuffer) ProtoMessage 

func (*ModelOptimizationPolicy_PinnedMemoryBuffer) ProtoMessage()

func (*ModelOptimizationPolicy_PinnedMemoryBuffer) ProtoReflect 

func (x *ModelOptimizationPolicy_PinnedMemoryBuffer) ProtoReflect() protoreflect.Message

func (*ModelOptimizationPolicy_PinnedMemoryBuffer) Reset 

func (x *ModelOptimizationPolicy_PinnedMemoryBuffer) Reset()

func (*ModelOptimizationPolicy_PinnedMemoryBuffer) String 

func (x *ModelOptimizationPolicy_PinnedMemoryBuffer) 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=inference.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"`
	//@@  .. cpp:var:: bool is_shape_tensor
	//@@
	//@@     Whether or not the output is a shape tensor to the model. This field
	//@@     is currently supported only for the TensorRT model. An error will be
	//@@     generated if this specification does not comply with underlying
	//@@     model.
	//@@
	IsShapeTensor bool `protobuf:"varint,6,opt,name=is_shape_tensor,json=isShapeTensor,proto3" json:"is_shape_tensor,omitempty"`
	// contains filtered or unexported fields
}

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

func (*ModelOutput) Descriptor deprecated 

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

Deprecated: Use ModelOutput.ProtoReflect.Descriptor instead.

func (*ModelOutput) GetDataType 

func (x *ModelOutput) GetDataType() DataType

func (*ModelOutput) GetDims 

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

func (*ModelOutput) GetIsShapeTensor 

func (x *ModelOutput) GetIsShapeTensor() bool

func (*ModelOutput) GetLabelFilename 

func (x *ModelOutput) GetLabelFilename() string

func (*ModelOutput) GetName 

func (x *ModelOutput) GetName() string

func (*ModelOutput) GetReshape 

func (x *ModelOutput) GetReshape() *ModelTensorReshape

func (*ModelOutput) ProtoMessage 

func (*ModelOutput) ProtoMessage()

func (*ModelOutput) ProtoReflect 

func (x *ModelOutput) ProtoReflect() protoreflect.Message

func (*ModelOutput) Reset 

func (x *ModelOutput) Reset()

func (*ModelOutput) String 

func (x *ModelOutput) String() string

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"`
	// contains filtered or unexported fields
}

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

func (*ModelParameter) Descriptor deprecated 

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

Deprecated: Use ModelParameter.ProtoReflect.Descriptor instead.

func (*ModelParameter) GetStringValue 

func (x *ModelParameter) GetStringValue() string

func (*ModelParameter) ProtoMessage 

func (*ModelParameter) ProtoMessage()

func (*ModelParameter) ProtoReflect 

func (x *ModelParameter) ProtoReflect() protoreflect.Message

func (*ModelParameter) Reset 

func (x *ModelParameter) Reset()

func (*ModelParameter) String 

func (x *ModelParameter) String() string

type ModelQueuePolicy 

type ModelQueuePolicy struct {

	//@@
	//@@  .. cpp:var:: TimeoutAction timeout_action
	//@@
	//@@     The action applied to timed-out request.
	//@@     The default action is REJECT.
	//@@
	TimeoutAction ModelQueuePolicy_TimeoutAction `` /* 147-byte string literal not displayed */
	//@@
	//@@  .. cpp:var:: uint64 default_timeout_microseconds
	//@@
	//@@     The default timeout for every request, in microseconds.
	//@@     The default value is 0 which indicates that no timeout is set.
	//@@
	DefaultTimeoutMicroseconds uint64 `` /* 142-byte string literal not displayed */
	//@@
	//@@  .. cpp:var:: bool allow_timeout_override
	//@@
	//@@     Whether individual request can override the default timeout value.
	//@@     When true, individual requests can set a timeout that is less than
	//@@     the default timeout value but may not increase the timeout.
	//@@     The default value is false.
	//@@
	AllowTimeoutOverride bool `protobuf:"varint,3,opt,name=allow_timeout_override,json=allowTimeoutOverride,proto3" json:"allow_timeout_override,omitempty"`
	//@@
	//@@  .. cpp:var:: uint32 max_queue_size
	//@@
	//@@     The maximum queue size for holding requests. A request will be
	//@@     rejected immediately if it can't be enqueued because the queue is
	//@@     full. The default value is 0 which indicates that no maximum
	//@@     queue size is enforced.
	//@@
	MaxQueueSize uint32 `protobuf:"varint,4,opt,name=max_queue_size,json=maxQueueSize,proto3" json:"max_queue_size,omitempty"`
	// contains filtered or unexported fields
}

@@ @@.. cpp:var:: message ModelQueuePolicy @@ @@ Queue policy for inference requests. @@

func (*ModelQueuePolicy) Descriptor deprecated 

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

Deprecated: Use ModelQueuePolicy.ProtoReflect.Descriptor instead.

func (*ModelQueuePolicy) GetAllowTimeoutOverride 

func (x *ModelQueuePolicy) GetAllowTimeoutOverride() bool

func (*ModelQueuePolicy) GetDefaultTimeoutMicroseconds 

func (x *ModelQueuePolicy) GetDefaultTimeoutMicroseconds() uint64

func (*ModelQueuePolicy) GetMaxQueueSize 

func (x *ModelQueuePolicy) GetMaxQueueSize() uint32

func (*ModelQueuePolicy) GetTimeoutAction 

func (x *ModelQueuePolicy) GetTimeoutAction() ModelQueuePolicy_TimeoutAction

func (*ModelQueuePolicy) ProtoMessage 

func (*ModelQueuePolicy) ProtoMessage()

func (*ModelQueuePolicy) ProtoReflect 

func (x *ModelQueuePolicy) ProtoReflect() protoreflect.Message

func (*ModelQueuePolicy) Reset 

func (x *ModelQueuePolicy) Reset()

func (*ModelQueuePolicy) String 

func (x *ModelQueuePolicy) String() string

type ModelQueuePolicy_TimeoutAction 

type ModelQueuePolicy_TimeoutAction int32

@@ @@ .. cpp:enum:: TimeoutAction @@ @@ The action applied to timed-out requests. @@ 

const (
	//@@    .. cpp:enumerator:: Action::REJECT = 0
	//@@
	//@@       Reject the request and return error message accordingly.
	//@@
	ModelQueuePolicy_REJECT ModelQueuePolicy_TimeoutAction = 0
	//@@    .. cpp:enumerator:: Action::DELAY = 1
	//@@
	//@@       Delay the request until all other requests at the same
	//@@       (or higher) priority levels that have not reached their timeouts
	//@@       are processed. A delayed request will eventually be processed,
	//@@       but may be delayed indefinitely due to newly arriving requests.
	//@@
	ModelQueuePolicy_DELAY ModelQueuePolicy_TimeoutAction = 1
)

func (ModelQueuePolicy_TimeoutAction) Descriptor 

func (ModelQueuePolicy_TimeoutAction) Descriptor() protoreflect.EnumDescriptor

func (ModelQueuePolicy_TimeoutAction) Enum 

func (x ModelQueuePolicy_TimeoutAction) Enum() *ModelQueuePolicy_TimeoutAction

func (ModelQueuePolicy_TimeoutAction) EnumDescriptor deprecated 

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

Deprecated: Use ModelQueuePolicy_TimeoutAction.Descriptor instead.

func (ModelQueuePolicy_TimeoutAction) Number 

func (x ModelQueuePolicy_TimeoutAction) Number() protoreflect.EnumNumber

func (ModelQueuePolicy_TimeoutAction) String 

func (x ModelQueuePolicy_TimeoutAction) String() string

func (ModelQueuePolicy_TimeoutAction) Type 

func (ModelQueuePolicy_TimeoutAction) Type() protoreflect.EnumType

type ModelRateLimiter 

type ModelRateLimiter struct {

	//@@  .. cpp:var:: Resource resources (repeated)
	//@@
	//@@     The resources required to execute the request on a model instance.
	//@@     Resources are just names with a corresponding count. The execution
	//@@     of the instance will be blocked until the specificied resources are
	//@@     available. By default an instance uses no rate-limiter resources.
	//@@
	Resources []*ModelRateLimiter_Resource `protobuf:"bytes,1,rep,name=resources,proto3" json:"resources,omitempty"`
	//@@  .. cpp:var:: uint32 priority
	//@@
	//@@     The optional weighting value to be used for prioritizing across
	//@@     instances. An instance with priority 2 will be given 1/2 the
	//@@     number of scheduling chances as an instance_group with priority
	//@@     1. The default priority is 1. The priority of value 0 will be
	//@@     treated as priority 1.
	//@@
	Priority uint32 `protobuf:"varint,2,opt,name=priority,proto3" json:"priority,omitempty"`
	// contains filtered or unexported fields
}

@@ @@ .. cpp:var:: message ModelRateLimiter @@ @@ The specifications required by the rate limiter to properly @@ schedule the inference requests across the different models @@ and their instances. @@

func (*ModelRateLimiter) Descriptor deprecated 

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

Deprecated: Use ModelRateLimiter.ProtoReflect.Descriptor instead.

func (*ModelRateLimiter) GetPriority 

func (x *ModelRateLimiter) GetPriority() uint32

func (*ModelRateLimiter) GetResources 

func (x *ModelRateLimiter) GetResources() []*ModelRateLimiter_Resource

func (*ModelRateLimiter) ProtoMessage 

func (*ModelRateLimiter) ProtoMessage()

func (*ModelRateLimiter) ProtoReflect 

func (x *ModelRateLimiter) ProtoReflect() protoreflect.Message

func (*ModelRateLimiter) Reset 

func (x *ModelRateLimiter) Reset()

func (*ModelRateLimiter) String 

func (x *ModelRateLimiter) String() string

type ModelRateLimiter_Resource 

type ModelRateLimiter_Resource struct {

	//@@  .. cpp:var:: string name
	//@@
	//@@     The name associated with the resource.
	//@@
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	//@@  .. cpp:var:: bool global
	//@@
	//@@     Whether or not the resource is global. If true then the resource
	//@@     is assumed to be shared among the devices otherwise specified
	//@@     count of the resource is assumed for each device associated
	//@@     with the instance.
	//@@
	Global bool `protobuf:"varint,2,opt,name=global,proto3" json:"global,omitempty"`
	//@@  .. cpp:var:: uint32 count
	//@@
	//@@     The number of resources required for the execution of the model
	//@@     instance.
	//@@
	Count uint32 `protobuf:"varint,3,opt,name=count,proto3" json:"count,omitempty"`
	// contains filtered or unexported fields
}

@@ .. cpp:var:: message Resource @@ @@ The resource property. @@

func (*ModelRateLimiter_Resource) Descriptor deprecated 

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

Deprecated: Use ModelRateLimiter_Resource.ProtoReflect.Descriptor instead.

func (*ModelRateLimiter_Resource) GetCount 

func (x *ModelRateLimiter_Resource) GetCount() uint32

func (*ModelRateLimiter_Resource) GetGlobal 

func (x *ModelRateLimiter_Resource) GetGlobal() bool

func (*ModelRateLimiter_Resource) GetName 

func (x *ModelRateLimiter_Resource) GetName() string

func (*ModelRateLimiter_Resource) ProtoMessage 

func (*ModelRateLimiter_Resource) ProtoMessage()

func (*ModelRateLimiter_Resource) ProtoReflect 

func (x *ModelRateLimiter_Resource) ProtoReflect() protoreflect.Message

func (*ModelRateLimiter_Resource) Reset 

func (x *ModelRateLimiter_Resource) Reset()

func (*ModelRateLimiter_Resource) String 

func (x *ModelRateLimiter_Resource) String() string

type ModelRepositoryAgents 

type ModelRepositoryAgents struct {

	//@@
	//@@  .. cpp:var:: Agent agents (repeated)
	//@@
	//@@     The ordered list of agents for the model. These agents will be
	//@@     invoked in order to respond to repository actions occuring for the
	//@@     model.
	//@@
	Agents []*ModelRepositoryAgents_Agent `protobuf:"bytes,1,rep,name=agents,proto3" json:"agents,omitempty"`
	// contains filtered or unexported fields
}

@@ @@.. cpp:var:: message ModelRepositoryAgents @@ @@ The repository agents for the model. @@

func (*ModelRepositoryAgents) Descriptor deprecated 

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

Deprecated: Use ModelRepositoryAgents.ProtoReflect.Descriptor instead.

func (*ModelRepositoryAgents) GetAgents 

func (x *ModelRepositoryAgents) GetAgents() []*ModelRepositoryAgents_Agent

func (*ModelRepositoryAgents) ProtoMessage 

func (*ModelRepositoryAgents) ProtoMessage()

func (*ModelRepositoryAgents) ProtoReflect 

func (x *ModelRepositoryAgents) ProtoReflect() protoreflect.Message

func (*ModelRepositoryAgents) Reset 

func (x *ModelRepositoryAgents) Reset()

func (*ModelRepositoryAgents) String 

func (x *ModelRepositoryAgents) String() string

type ModelRepositoryAgents_Agent 

type ModelRepositoryAgents_Agent struct {

	//@@    .. cpp:var:: string name
	//@@
	//@@       The name of the agent.
	//@@
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	//@@    .. cpp:var:: map<string, string> parameters
	//@@
	//@@       The parameters for the agent.
	//@@
	Parameters map[string]string `` /* 161-byte string literal not displayed */
	// contains filtered or unexported fields
}

@@ @@ .. cpp:var:: message Agent @@ @@ A repository agent that should be invoked for the specified @@ repository actions for this model. @@

func (*ModelRepositoryAgents_Agent) Descriptor deprecated 

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

Deprecated: Use ModelRepositoryAgents_Agent.ProtoReflect.Descriptor instead.

func (*ModelRepositoryAgents_Agent) GetName 

func (x *ModelRepositoryAgents_Agent) GetName() string

func (*ModelRepositoryAgents_Agent) GetParameters 

func (x *ModelRepositoryAgents_Agent) GetParameters() map[string]string

func (*ModelRepositoryAgents_Agent) ProtoMessage 

func (*ModelRepositoryAgents_Agent) ProtoMessage()

func (*ModelRepositoryAgents_Agent) ProtoReflect 

func (x *ModelRepositoryAgents_Agent) ProtoReflect() protoreflect.Message

func (*ModelRepositoryAgents_Agent) Reset 

func (x *ModelRepositoryAgents_Agent) Reset()

func (*ModelRepositoryAgents_Agent) String 

func (x *ModelRepositoryAgents_Agent) String() string

type ModelResponseCache 

type ModelResponseCache struct {

	//@@
	//@@  .. cpp::var:: bool enable
	//@@
	//@@     Whether or not to use response cache for the model. If True, the
	//@@     responses from the model are cached and when identical request
	//@@     is encountered, instead of going through the model execution,
	//@@     the response from the cache is utilized. By default, response
	//@@     cache is disabled for the models.
	//@@
	Enable bool `protobuf:"varint,1,opt,name=enable,proto3" json:"enable,omitempty"`
	// contains filtered or unexported fields
}

@@ @@.. cpp:var:: message ModelResponseCache @@ @@ The response cache setting for the model. @@

func (*ModelResponseCache) Descriptor deprecated 

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

Deprecated: Use ModelResponseCache.ProtoReflect.Descriptor instead.

func (*ModelResponseCache) GetEnable 

func (x *ModelResponseCache) GetEnable() bool

func (*ModelResponseCache) ProtoMessage 

func (*ModelResponseCache) ProtoMessage()

func (*ModelResponseCache) ProtoReflect 

func (x *ModelResponseCache) ProtoReflect() protoreflect.Message

func (*ModelResponseCache) Reset 

func (x *ModelResponseCache) Reset()

func (*ModelResponseCache) String 

func (x *ModelResponseCache) String() string

type ModelSequenceBatching 

type ModelSequenceBatching struct {

	//@@  .. cpp:var:: oneof strategy_choice
	//@@
	//@@     The strategy used by the sequence batcher. Default strategy
	//@@     is 'direct'.
	//@@
	//
	// Types that are assignable to StrategyChoice:
	//	*ModelSequenceBatching_Direct
	//	*ModelSequenceBatching_Oldest
	StrategyChoice isModelSequenceBatching_StrategyChoice `protobuf_oneof:"strategy_choice"`
	//@@  .. 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 sequence 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"`
	//@@  .. cpp:var:: State state (repeated)
	//@@
	//@@     The optional state that can be stored in Triton for performing
	//@@     inference requests on a sequence. Each sequence holds an implicit
	//@@     state local to itself. The output state tensor provided by the
	//@@     model in 'output_name' field of the current inference request will
	//@@     be transferred as an input tensor named 'input_name' in the next
	//@@     request of the same sequence. The input state of the first request
	//@@     in the sequence contains garbage data.
	//@@
	State []*ModelSequenceBatching_State `protobuf:"bytes,5,rep,name=state,proto3" json:"state,omitempty"`
	// contains filtered or unexported fields
}

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

func (*ModelSequenceBatching) Descriptor deprecated 

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

Deprecated: Use ModelSequenceBatching.ProtoReflect.Descriptor instead.

func (*ModelSequenceBatching) GetControlInput 

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

func (*ModelSequenceBatching) GetDirect 

func (x *ModelSequenceBatching) GetDirect() *ModelSequenceBatching_StrategyDirect

func (*ModelSequenceBatching) GetMaxSequenceIdleMicroseconds 

func (x *ModelSequenceBatching) GetMaxSequenceIdleMicroseconds() uint64

func (*ModelSequenceBatching) GetOldest 

func (x *ModelSequenceBatching) GetOldest() *ModelSequenceBatching_StrategyOldest

func (*ModelSequenceBatching) GetState 

func (x *ModelSequenceBatching) GetState() []*ModelSequenceBatching_State

func (*ModelSequenceBatching) GetStrategyChoice 

func (m *ModelSequenceBatching) GetStrategyChoice() isModelSequenceBatching_StrategyChoice

func (*ModelSequenceBatching) ProtoMessage 

func (*ModelSequenceBatching) ProtoMessage()

func (*ModelSequenceBatching) ProtoReflect 

func (x *ModelSequenceBatching) ProtoReflect() protoreflect.Message

func (*ModelSequenceBatching) Reset 

func (x *ModelSequenceBatching) Reset()

func (*ModelSequenceBatching) String 

func (x *ModelSequenceBatching) String() string

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=inference.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"`
	//@@    .. cpp:var:: bool bool_false_true (repeated)
	//@@
	//@@       The control's true and false setting is indicated by setting
	//@@       a value in a bool tensor. The tensor must be a
	//@@       1-dimensional tensor with size equal to the batch size of
	//@@       the request. 'bool_false_true' must have two entries: the
	//@@       first the false value and the second the true value.
	//@@
	BoolFalseTrue []bool `protobuf:"varint,5,rep,packed,name=bool_false_true,json=boolFalseTrue,proto3" json:"bool_false_true,omitempty"`
	//@@    .. cpp:var:: DataType data_type
	//@@
	//@@       The control's datatype.
	//@@
	DataType DataType `protobuf:"varint,4,opt,name=data_type,json=dataType,proto3,enum=inference.DataType" json:"data_type,omitempty"`
	// contains filtered or unexported fields
}

@@ .. cpp:var:: message Control @@ @@ A control is a signal that the sequence batcher uses to @@ communicate with a backend. @@

func (*ModelSequenceBatching_Control) Descriptor deprecated 

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

Deprecated: Use ModelSequenceBatching_Control.ProtoReflect.Descriptor instead.

func (*ModelSequenceBatching_Control) GetBoolFalseTrue 

func (x *ModelSequenceBatching_Control) GetBoolFalseTrue() []bool

func (*ModelSequenceBatching_Control) GetDataType 

func (x *ModelSequenceBatching_Control) GetDataType() DataType

func (*ModelSequenceBatching_Control) GetFp32FalseTrue 

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

func (*ModelSequenceBatching_Control) GetInt32FalseTrue 

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

func (*ModelSequenceBatching_Control) GetKind 

func (x *ModelSequenceBatching_Control) GetKind() ModelSequenceBatching_Control_Kind

func (*ModelSequenceBatching_Control) ProtoMessage 

func (*ModelSequenceBatching_Control) ProtoMessage()

func (*ModelSequenceBatching_Control) ProtoReflect 

func (x *ModelSequenceBatching_Control) ProtoReflect() protoreflect.Message

func (*ModelSequenceBatching_Control) Reset 

func (x *ModelSequenceBatching_Control) Reset()

func (*ModelSequenceBatching_Control) String 

func (x *ModelSequenceBatching_Control) String() string

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"`
	// contains filtered or unexported fields
}

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

func (*ModelSequenceBatching_ControlInput) Descriptor deprecated 

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

Deprecated: Use ModelSequenceBatching_ControlInput.ProtoReflect.Descriptor instead.

func (*ModelSequenceBatching_ControlInput) GetControl 

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

func (*ModelSequenceBatching_ControlInput) GetName 

func (x *ModelSequenceBatching_ControlInput) GetName() string

func (*ModelSequenceBatching_ControlInput) ProtoMessage 

func (*ModelSequenceBatching_ControlInput) ProtoMessage()

func (*ModelSequenceBatching_ControlInput) ProtoReflect 

func (x *ModelSequenceBatching_ControlInput) ProtoReflect() protoreflect.Message

func (*ModelSequenceBatching_ControlInput) Reset 

func (x *ModelSequenceBatching_ControlInput) Reset()

func (*ModelSequenceBatching_ControlInput) String 

func (x *ModelSequenceBatching_ControlInput) String() string

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. Must
	//@@         specify either int32_false_true, fp32_false_true or
	//@@         bool_false_true for this control. This control is optional.
	//@@
	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". Must specify either int32_false_true,
	//@@         fp32_false_true or bool_false_true for this control. This
	//@@         control is optional.
	//@@
	ModelSequenceBatching_Control_CONTROL_SEQUENCE_READY ModelSequenceBatching_Control_Kind = 1
	//@@      .. cpp:enumerator:: Kind::CONTROL_SEQUENCE_END = 2
	//@@
	//@@         A sequence is/is-not ending. If true a sequence is
	//@@         ending, if false a sequence is continuing. Must specify
	//@@         either int32_false_true, fp32_false_true or bool_false_true
	//@@         for this control. This control is optional.
	//@@
	ModelSequenceBatching_Control_CONTROL_SEQUENCE_END ModelSequenceBatching_Control_Kind = 2
	//@@      .. cpp:enumerator:: Kind::CONTROL_SEQUENCE_CORRID = 3
	//@@
	//@@         The correlation ID of the sequence. The correlation ID
	//@@         is an uint64_t value that is communicated in whole or
	//@@         in part by the tensor. The tensor's datatype must be
	//@@         specified by data_type and must be TYPE_UINT64, TYPE_INT64,
	//@@         TYPE_UINT32 or TYPE_INT32. If a 32-bit datatype is specified
	//@@         the correlation ID will be truncated to the low-order 32
	//@@         bits. This control is optional.
	//@@
	ModelSequenceBatching_Control_CONTROL_SEQUENCE_CORRID ModelSequenceBatching_Control_Kind = 3
)

func (ModelSequenceBatching_Control_Kind) Descriptor 

func (ModelSequenceBatching_Control_Kind) Descriptor() protoreflect.EnumDescriptor

func (ModelSequenceBatching_Control_Kind) Enum 

func (x ModelSequenceBatching_Control_Kind) Enum() *ModelSequenceBatching_Control_Kind

func (ModelSequenceBatching_Control_Kind) EnumDescriptor deprecated 

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

Deprecated: Use ModelSequenceBatching_Control_Kind.Descriptor instead.

func (ModelSequenceBatching_Control_Kind) Number 

func (x ModelSequenceBatching_Control_Kind) Number() protoreflect.EnumNumber

func (ModelSequenceBatching_Control_Kind) String 

func (x ModelSequenceBatching_Control_Kind) String() string

func (ModelSequenceBatching_Control_Kind) Type 

func (ModelSequenceBatching_Control_Kind) Type() protoreflect.EnumType

type ModelSequenceBatching_Direct 

type ModelSequenceBatching_Direct struct {
	//@@    .. cpp:var:: StrategyDirect direct
	//@@
	//@@       StrategyDirect scheduling strategy.
	//@@
	Direct *ModelSequenceBatching_StrategyDirect `protobuf:"bytes,3,opt,name=direct,proto3,oneof"`
}

type ModelSequenceBatching_InitialState 

type ModelSequenceBatching_InitialState struct {

	//@@      .. cpp:var:: DataType data_type
	//@@
	//@@         The data-type of the state.
	//@@
	DataType DataType `protobuf:"varint,1,opt,name=data_type,json=dataType,proto3,enum=inference.DataType" json:"data_type,omitempty"`
	//@@      .. cpp:var:: int64 dims (repeated)
	//@@
	//@@         The shape of the state tensor, not including the batch dimension.
	//@@
	Dims []int64 `protobuf:"varint,2,rep,packed,name=dims,proto3" json:"dims,omitempty"`
	//@@      .. cpp:var:: oneof state_data
	//@@
	//@@         Specify how the initial state data is generated.
	//@@
	//
	// Types that are assignable to StateData:
	//	*ModelSequenceBatching_InitialState_ZeroData
	//	*ModelSequenceBatching_InitialState_DataFile
	StateData isModelSequenceBatching_InitialState_StateData `protobuf_oneof:"state_data"`
	//@@  .. cpp:var:: string name
	//@@
	//@@     The name of the state initialization.
	//@@
	Name string `protobuf:"bytes,5,opt,name=name,proto3" json:"name,omitempty"`
	// contains filtered or unexported fields
}

@@ @@ .. cpp:var:: message InitialState @@ @@ Settings used to initialize data for implicit state. @@

func (*ModelSequenceBatching_InitialState) Descriptor deprecated 

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

Deprecated: Use ModelSequenceBatching_InitialState.ProtoReflect.Descriptor instead.

func (*ModelSequenceBatching_InitialState) GetDataFile 

func (x *ModelSequenceBatching_InitialState) GetDataFile() string

func (*ModelSequenceBatching_InitialState) GetDataType 

func (x *ModelSequenceBatching_InitialState) GetDataType() DataType

func (*ModelSequenceBatching_InitialState) GetDims 

func (x *ModelSequenceBatching_InitialState) GetDims() []int64

func (*ModelSequenceBatching_InitialState) GetName 

func (x *ModelSequenceBatching_InitialState) GetName() string

func (*ModelSequenceBatching_InitialState) GetStateData 

func (m *ModelSequenceBatching_InitialState) GetStateData() isModelSequenceBatching_InitialState_StateData

func (*ModelSequenceBatching_InitialState) GetZeroData 

func (x *ModelSequenceBatching_InitialState) GetZeroData() bool

func (*ModelSequenceBatching_InitialState) ProtoMessage 

func (*ModelSequenceBatching_InitialState) ProtoMessage()

func (*ModelSequenceBatching_InitialState) ProtoReflect 

func (x *ModelSequenceBatching_InitialState) ProtoReflect() protoreflect.Message

func (*ModelSequenceBatching_InitialState) Reset 

func (x *ModelSequenceBatching_InitialState) Reset()

func (*ModelSequenceBatching_InitialState) String 

func (x *ModelSequenceBatching_InitialState) String() string

type ModelSequenceBatching_InitialState_DataFile 

type ModelSequenceBatching_InitialState_DataFile struct {
	//@@      .. cpp:var:: string data_file
	//@@
	//@@         The file whose content will be used as the initial data for
	//@@         the state in row-major order. The file must be provided in
	//@@         sub-directory 'initial_state' under the model directory.
	//@@
	DataFile string `protobuf:"bytes,4,opt,name=data_file,json=dataFile,proto3,oneof"`
}

type ModelSequenceBatching_InitialState_ZeroData 

type ModelSequenceBatching_InitialState_ZeroData struct {
	//@@
	//@@      .. cpp:var:: bool zero_data
	//@@
	//@@         The identifier for using zeros as initial state data.
	//@@         Note that the value of 'zero_data' will not be checked,
	//@@         instead, zero data will be used as long as the field is set.
	//@@
	ZeroData bool `protobuf:"varint,3,opt,name=zero_data,json=zeroData,proto3,oneof"`
}

type ModelSequenceBatching_Oldest 

type ModelSequenceBatching_Oldest struct {
	//@@    .. cpp:var:: StrategyOldest oldest
	//@@
	//@@       StrategyOldest scheduling strategy.
	//@@
	Oldest *ModelSequenceBatching_StrategyOldest `protobuf:"bytes,4,opt,name=oldest,proto3,oneof"`
}

type ModelSequenceBatching_State 

type ModelSequenceBatching_State struct {

	//@@    .. cpp:var:: string input_name
	//@@
	//@@       The name of the model state input.
	//@@
	InputName string `protobuf:"bytes,1,opt,name=input_name,json=inputName,proto3" json:"input_name,omitempty"`
	//@@    .. cpp:var:: string output_name
	//@@
	//@@       The name of the model state output.
	//@@
	OutputName string `protobuf:"bytes,2,opt,name=output_name,json=outputName,proto3" json:"output_name,omitempty"`
	//@@    .. cpp:var:: DataType data_type
	//@@
	//@@       The data-type of the state.
	//@@
	DataType DataType `protobuf:"varint,3,opt,name=data_type,json=dataType,proto3,enum=inference.DataType" json:"data_type,omitempty"`
	//@@    .. cpp:var:: int64 dim (repeated)
	//@@
	//@@       The dimension.
	//@@
	Dims []int64 `protobuf:"varint,4,rep,packed,name=dims,proto3" json:"dims,omitempty"`
	//@@  .. cpp:var:: InitialState initial_state (repeated)
	//@@
	//@@     The optional field to specify the initial state for the model.
	//@@
	InitialState []*ModelSequenceBatching_InitialState `protobuf:"bytes,5,rep,name=initial_state,json=initialState,proto3" json:"initial_state,omitempty"`
	// contains filtered or unexported fields
}

@@ .. cpp:var:: message State @@ @@ An input / output pair of tensors that carry state for the sequence. @@

func (*ModelSequenceBatching_State) Descriptor deprecated 

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

Deprecated: Use ModelSequenceBatching_State.ProtoReflect.Descriptor instead.

func (*ModelSequenceBatching_State) GetDataType 

func (x *ModelSequenceBatching_State) GetDataType() DataType

func (*ModelSequenceBatching_State) GetDims 

func (x *ModelSequenceBatching_State) GetDims() []int64

func (*ModelSequenceBatching_State) GetInitialState 

func (x *ModelSequenceBatching_State) GetInitialState() []*ModelSequenceBatching_InitialState

func (*ModelSequenceBatching_State) GetInputName 

func (x *ModelSequenceBatching_State) GetInputName() string

func (*ModelSequenceBatching_State) GetOutputName 

func (x *ModelSequenceBatching_State) GetOutputName() string

func (*ModelSequenceBatching_State) ProtoMessage 

func (*ModelSequenceBatching_State) ProtoMessage()

func (*ModelSequenceBatching_State) ProtoReflect 

func (x *ModelSequenceBatching_State) ProtoReflect() protoreflect.Message

func (*ModelSequenceBatching_State) Reset 

func (x *ModelSequenceBatching_State) Reset()

func (*ModelSequenceBatching_State) String 

func (x *ModelSequenceBatching_State) String() string

type ModelSequenceBatching_StrategyDirect 

type ModelSequenceBatching_StrategyDirect struct {

	//@@    .. cpp:var:: uint64 max_queue_delay_microseconds
	//@@
	//@@       The maximum time, in microseconds, a candidate request
	//@@       will be delayed in the sequence batch scheduling queue to
	//@@       wait for additional requests for batching. Default is 0.
	//@@
	MaxQueueDelayMicroseconds uint64 `` /* 141-byte string literal not displayed */
	//@@    .. cpp:var:: float minimum_slot_utilization
	//@@
	//@@       The minimum slot utilization that must be satisfied to
	//@@       execute the batch before 'max_queue_delay_microseconds' expires.
	//@@       For example, a value of 0.5 indicates that the batch should be
	//@@       executed as soon as 50% or more of the slots are ready even if
	//@@       the 'max_queue_delay_microseconds' timeout has not expired.
	//@@       The default is 0.0, indicating that a batch will be executed
	//@@       before 'max_queue_delay_microseconds' timeout expires if at least
	//@@       one batch slot is ready. 'max_queue_delay_microseconds' will be
	//@@       ignored unless minimum_slot_utilization is set to a non-zero
	//@@       value.
	//@@
	MinimumSlotUtilization float32 `` /* 131-byte string literal not displayed */
	// contains filtered or unexported fields
}

@@ .. cpp:var:: message StrategyDirect @@ @@ The sequence batcher uses a specific, unique batch @@ slot for each sequence. All inference requests in a @@ sequence are directed to the same batch slot in the same @@ model instance over the lifetime of the sequence. This @@ is the default strategy. @@

func (*ModelSequenceBatching_StrategyDirect) Descriptor deprecated 

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

Deprecated: Use ModelSequenceBatching_StrategyDirect.ProtoReflect.Descriptor instead.

func (*ModelSequenceBatching_StrategyDirect) GetMaxQueueDelayMicroseconds 

func (x *ModelSequenceBatching_StrategyDirect) GetMaxQueueDelayMicroseconds() uint64

func (*ModelSequenceBatching_StrategyDirect) GetMinimumSlotUtilization 

func (x *ModelSequenceBatching_StrategyDirect) GetMinimumSlotUtilization() float32

func (*ModelSequenceBatching_StrategyDirect) ProtoMessage 

func (*ModelSequenceBatching_StrategyDirect) ProtoMessage()

func (*ModelSequenceBatching_StrategyDirect) ProtoReflect 

func (x *ModelSequenceBatching_StrategyDirect) ProtoReflect() protoreflect.Message

func (*ModelSequenceBatching_StrategyDirect) Reset 

func (x *ModelSequenceBatching_StrategyDirect) Reset()

func (*ModelSequenceBatching_StrategyDirect) String 

func (x *ModelSequenceBatching_StrategyDirect) String() string

type ModelSequenceBatching_StrategyOldest 

type ModelSequenceBatching_StrategyOldest struct {

	//@@    .. cpp:var:: int32 max_candidate_sequences
	//@@
	//@@       Maximum number of candidate sequences that the batcher
	//@@       maintains. Excess seqences are kept in an ordered backlog
	//@@       and become candidates when existing candidate sequences
	//@@       complete.
	//@@
	MaxCandidateSequences int32 `` /* 127-byte string literal not displayed */
	//@@    .. cpp:var:: int32 preferred_batch_size (repeated)
	//@@
	//@@       Preferred batch sizes for dynamic batching of candidate
	//@@       sequences. 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,2,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 candidate request
	//@@       will be delayed in the dynamic batch scheduling queue to
	//@@       wait for additional requests for batching. Default is 0.
	//@@
	MaxQueueDelayMicroseconds uint64 `` /* 141-byte string literal not displayed */
	// contains filtered or unexported fields
}

@@ .. cpp:var:: message StrategyOldest @@ @@ The sequence batcher maintains up to 'max_candidate_sequences' @@ candidate sequences. 'max_candidate_sequences' can be greater @@ than the model's 'max_batch_size'. For inferencing the batcher @@ chooses from the candidate sequences up to 'max_batch_size' @@ inference requests. Requests are chosen in an oldest-first @@ manner across all candidate sequences. A given sequence is @@ not guaranteed to be assigned to the same batch slot for @@ all inference requests of that sequence. @@

func (*ModelSequenceBatching_StrategyOldest) Descriptor deprecated 

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

Deprecated: Use ModelSequenceBatching_StrategyOldest.ProtoReflect.Descriptor instead.

func (*ModelSequenceBatching_StrategyOldest) GetMaxCandidateSequences 

func (x *ModelSequenceBatching_StrategyOldest) GetMaxCandidateSequences() int32

func (*ModelSequenceBatching_StrategyOldest) GetMaxQueueDelayMicroseconds 

func (x *ModelSequenceBatching_StrategyOldest) GetMaxQueueDelayMicroseconds() uint64

func (*ModelSequenceBatching_StrategyOldest) GetPreferredBatchSize 

func (x *ModelSequenceBatching_StrategyOldest) GetPreferredBatchSize() []int32

func (*ModelSequenceBatching_StrategyOldest) ProtoMessage 

func (*ModelSequenceBatching_StrategyOldest) ProtoMessage()

func (*ModelSequenceBatching_StrategyOldest) ProtoReflect 

func (x *ModelSequenceBatching_StrategyOldest) ProtoReflect() protoreflect.Message

func (*ModelSequenceBatching_StrategyOldest) Reset 

func (x *ModelSequenceBatching_StrategyOldest) Reset()

func (*ModelSequenceBatching_StrategyOldest) String 

func (x *ModelSequenceBatching_StrategyOldest) String() string

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"`
	// contains filtered or unexported fields
}

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

func (*ModelTensorReshape) Descriptor deprecated 

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

Deprecated: Use ModelTensorReshape.ProtoReflect.Descriptor instead.

func (*ModelTensorReshape) GetShape 

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

func (*ModelTensorReshape) ProtoMessage 

func (*ModelTensorReshape) ProtoMessage()

func (*ModelTensorReshape) ProtoReflect 

func (x *ModelTensorReshape) ProtoReflect() protoreflect.Message

func (*ModelTensorReshape) Reset 

func (x *ModelTensorReshape) Reset()

func (*ModelTensorReshape) String 

func (x *ModelTensorReshape) String() string

type ModelTransactionPolicy 

type ModelTransactionPolicy struct {

	//@@  .. cpp:var:: bool decoupled
	//@@
	//@@     Indicates whether responses generated by the model are decoupled with
	//@@     the requests issued to it, which means the number of responses
	//@@     generated by model may differ from number of requests issued, and
	//@@     that the responses may be out of order relative to the order of
	//@@     requests. The default is false, which means the model will generate
	//@@     exactly one response for each request.
	//@@
	Decoupled bool `protobuf:"varint,1,opt,name=decoupled,proto3" json:"decoupled,omitempty"`
	// contains filtered or unexported fields
}

@@ @@ .. cpp:var:: message ModelTransactionPolicy @@ @@ The specification that describes the nature of transactions @@ to be expected from the model. @@

func (*ModelTransactionPolicy) Descriptor deprecated 

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

Deprecated: Use ModelTransactionPolicy.ProtoReflect.Descriptor instead.

func (*ModelTransactionPolicy) GetDecoupled 

func (x *ModelTransactionPolicy) GetDecoupled() bool

func (*ModelTransactionPolicy) ProtoMessage 

func (*ModelTransactionPolicy) ProtoMessage()

func (*ModelTransactionPolicy) ProtoReflect 

func (x *ModelTransactionPolicy) ProtoReflect() protoreflect.Message

func (*ModelTransactionPolicy) Reset 

func (x *ModelTransactionPolicy) Reset()

func (*ModelTransactionPolicy) String 

func (x *ModelTransactionPolicy) String() string

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 assignable to PolicyChoice:
	//	*ModelVersionPolicy_Latest_
	//	*ModelVersionPolicy_All_
	//	*ModelVersionPolicy_Specific_
	PolicyChoice isModelVersionPolicy_PolicyChoice `protobuf_oneof:"policy_choice"`
	// contains filtered or unexported fields
}

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

func (*ModelVersionPolicy) Descriptor deprecated 

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

Deprecated: Use ModelVersionPolicy.ProtoReflect.Descriptor instead.

func (*ModelVersionPolicy) GetAll 

func (x *ModelVersionPolicy) GetAll() *ModelVersionPolicy_All

func (*ModelVersionPolicy) GetLatest 

func (x *ModelVersionPolicy) GetLatest() *ModelVersionPolicy_Latest

func (*ModelVersionPolicy) GetPolicyChoice 

func (m *ModelVersionPolicy) GetPolicyChoice() isModelVersionPolicy_PolicyChoice

func (*ModelVersionPolicy) GetSpecific 

func (x *ModelVersionPolicy) GetSpecific() *ModelVersionPolicy_Specific

func (*ModelVersionPolicy) ProtoMessage 

func (*ModelVersionPolicy) ProtoMessage()

func (*ModelVersionPolicy) ProtoReflect 

func (x *ModelVersionPolicy) ProtoReflect() protoreflect.Message

func (*ModelVersionPolicy) Reset 

func (x *ModelVersionPolicy) Reset()

func (*ModelVersionPolicy) String 

func (x *ModelVersionPolicy) String() string

type ModelVersionPolicy_All 

type ModelVersionPolicy_All struct {
	// contains filtered or unexported fields
}

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

func (*ModelVersionPolicy_All) Descriptor deprecated 

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

Deprecated: Use ModelVersionPolicy_All.ProtoReflect.Descriptor instead.

func (*ModelVersionPolicy_All) ProtoMessage 

func (*ModelVersionPolicy_All) ProtoMessage()

func (*ModelVersionPolicy_All) ProtoReflect 

func (x *ModelVersionPolicy_All) ProtoReflect() protoreflect.Message

func (*ModelVersionPolicy_All) Reset 

func (x *ModelVersionPolicy_All) Reset()

func (*ModelVersionPolicy_All) String 

func (x *ModelVersionPolicy_All) String() string

type ModelVersionPolicy_All_ 

type ModelVersionPolicy_All_ struct {
	//@@    .. cpp:var:: All all
	//@@
	//@@       Serve all versions of the model.
	//@@
	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"`
	// contains filtered or unexported fields
}

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

func (*ModelVersionPolicy_Latest) Descriptor deprecated 

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

Deprecated: Use ModelVersionPolicy_Latest.ProtoReflect.Descriptor instead.

func (*ModelVersionPolicy_Latest) GetNumVersions 

func (x *ModelVersionPolicy_Latest) GetNumVersions() uint32

func (*ModelVersionPolicy_Latest) ProtoMessage 

func (*ModelVersionPolicy_Latest) ProtoMessage()

func (*ModelVersionPolicy_Latest) ProtoReflect 

func (x *ModelVersionPolicy_Latest) ProtoReflect() protoreflect.Message

func (*ModelVersionPolicy_Latest) Reset 

func (x *ModelVersionPolicy_Latest) Reset()

func (*ModelVersionPolicy_Latest) String 

func (x *ModelVersionPolicy_Latest) String() string

type ModelVersionPolicy_Latest_ 

type ModelVersionPolicy_Latest_ struct {
	//@@    .. cpp:var:: Latest latest
	//@@
	//@@       Serve only latest version(s) of the model.
	//@@
	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"`
	// contains filtered or unexported fields
}

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

func (*ModelVersionPolicy_Specific) Descriptor deprecated 

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

Deprecated: Use ModelVersionPolicy_Specific.ProtoReflect.Descriptor instead.

func (*ModelVersionPolicy_Specific) GetVersions 

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

func (*ModelVersionPolicy_Specific) ProtoMessage 

func (*ModelVersionPolicy_Specific) ProtoMessage()

func (*ModelVersionPolicy_Specific) ProtoReflect 

func (x *ModelVersionPolicy_Specific) ProtoReflect() protoreflect.Message

func (*ModelVersionPolicy_Specific) Reset 

func (x *ModelVersionPolicy_Specific) Reset()

func (*ModelVersionPolicy_Specific) String 

func (x *ModelVersionPolicy_Specific) String() string

type ModelVersionPolicy_Specific_ 

type ModelVersionPolicy_Specific_ struct {
	//@@    .. cpp:var:: Specific specific
	//@@
	//@@       Serve only specific version(s) of the model.
	//@@
	Specific *ModelVersionPolicy_Specific `protobuf:"bytes,3,opt,name=specific,proto3,oneof"`
}

type ModelWarmup 

type ModelWarmup struct {

	//@@  .. cpp:var:: string name
	//@@
	//@@     The name of the request sample.
	//@@
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,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. If
	//@@     batch_size > 1, the 'inputs' specified below will be duplicated to
	//@@     match the batch size requested.
	//@@
	BatchSize uint32 `protobuf:"varint,2,opt,name=batch_size,json=batchSize,proto3" json:"batch_size,omitempty"`
	//@@  .. cpp:var:: map<string, Input> inputs
	//@@
	//@@     The warmup meta data associated with every model input, including
	//@@     control tensors.
	//@@
	Inputs map[string]*ModelWarmup_Input `` /* 153-byte string literal not displayed */
	// contains filtered or unexported fields
}

@@ @@.. cpp:var:: message ModelWarmup @@ @@ Settings used to construct the request sample for model warmup. @@

func (*ModelWarmup) Descriptor deprecated 

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

Deprecated: Use ModelWarmup.ProtoReflect.Descriptor instead.

func (*ModelWarmup) GetBatchSize 

func (x *ModelWarmup) GetBatchSize() uint32

func (*ModelWarmup) GetInputs 

func (x *ModelWarmup) GetInputs() map[string]*ModelWarmup_Input

func (*ModelWarmup) GetName 

func (x *ModelWarmup) GetName() string

func (*ModelWarmup) ProtoMessage 

func (*ModelWarmup) ProtoMessage()

func (*ModelWarmup) ProtoReflect 

func (x *ModelWarmup) ProtoReflect() protoreflect.Message

func (*ModelWarmup) Reset 

func (x *ModelWarmup) Reset()

func (*ModelWarmup) String 

func (x *ModelWarmup) String() string

type ModelWarmup_Input 

type ModelWarmup_Input struct {

	//@@    .. cpp:var:: DataType data_type
	//@@
	//@@       The data-type of the input.
	//@@
	DataType DataType `protobuf:"varint,1,opt,name=data_type,json=dataType,proto3,enum=inference.DataType" json:"data_type,omitempty"`
	//@@    .. cpp:var:: int64 dims (repeated)
	//@@
	//@@       The shape of the input tensor, not including the batch dimension.
	//@@
	Dims []int64 `protobuf:"varint,2,rep,packed,name=dims,proto3" json:"dims,omitempty"`
	//@@    .. cpp:var:: oneof input_data_type
	//@@
	//@@       Specify how the input data is generated. If the input has STRING
	//@@       data type and 'random_data' is set, the data generation will fall
	//@@       back to 'zero_data'.
	//@@
	//
	// Types that are assignable to InputDataType:
	//	*ModelWarmup_Input_ZeroData
	//	*ModelWarmup_Input_RandomData
	//	*ModelWarmup_Input_InputDataFile
	InputDataType isModelWarmup_Input_InputDataType `protobuf_oneof:"input_data_type"`
	// contains filtered or unexported fields
}

@@ @@ .. cpp:var:: message Input @@ @@ Meta data associated with an input. @@

func (*ModelWarmup_Input) Descriptor deprecated 

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

Deprecated: Use ModelWarmup_Input.ProtoReflect.Descriptor instead.

func (*ModelWarmup_Input) GetDataType 

func (x *ModelWarmup_Input) GetDataType() DataType

func (*ModelWarmup_Input) GetDims 

func (x *ModelWarmup_Input) GetDims() []int64

func (*ModelWarmup_Input) GetInputDataFile 

func (x *ModelWarmup_Input) GetInputDataFile() string

func (*ModelWarmup_Input) GetInputDataType 

func (m *ModelWarmup_Input) GetInputDataType() isModelWarmup_Input_InputDataType

func (*ModelWarmup_Input) GetRandomData 

func (x *ModelWarmup_Input) GetRandomData() bool

func (*ModelWarmup_Input) GetZeroData 

func (x *ModelWarmup_Input) GetZeroData() bool

func (*ModelWarmup_Input) ProtoMessage 

func (*ModelWarmup_Input) ProtoMessage()

func (*ModelWarmup_Input) ProtoReflect 

func (x *ModelWarmup_Input) ProtoReflect() protoreflect.Message

func (*ModelWarmup_Input) Reset 

func (x *ModelWarmup_Input) Reset()

func (*ModelWarmup_Input) String 

func (x *ModelWarmup_Input) String() string

type ModelWarmup_Input_InputDataFile 

type ModelWarmup_Input_InputDataFile struct {
	//@@    .. cpp:var:: string input_data_file
	//@@
	//@@       The file whose content will be used as raw input data in
	//@@       row-major order. The file must be provided in a sub-directory
	//@@       'warmup' under the model directory.
	//@@
	InputDataFile string `protobuf:"bytes,5,opt,name=input_data_file,json=inputDataFile,proto3,oneof"`
}

type ModelWarmup_Input_RandomData 

type ModelWarmup_Input_RandomData struct {
	//@@
	//@@    .. cpp:var:: bool random_data
	//@@
	//@@       The identifier for using random data as input data. Note that
	//@@       the value of 'random_data' will not be checked, instead,
	//@@       random data will be used as long as the field is set.
	//@@
	RandomData bool `protobuf:"varint,4,opt,name=random_data,json=randomData,proto3,oneof"`
}

type ModelWarmup_Input_ZeroData 

type ModelWarmup_Input_ZeroData struct {
	//@@
	//@@    .. cpp:var:: bool zero_data
	//@@
	//@@       The identifier for using zeros as input data. Note that the
	//@@       value of 'zero_data' will not be checked, instead, zero data
	//@@       will be used as long as the field is set.
	//@@
	ZeroData bool `protobuf:"varint,3,opt,name=zero_data,json=zeroData,proto3,oneof"`
}

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.