List of all items
Structs
- TritonClient
- TritonModelBase
- inference::BatchInput
- inference::BatchOutput
- inference::CudaSharedMemoryRegisterRequest
- inference::CudaSharedMemoryRegisterResponse
- inference::CudaSharedMemoryStatusRequest
- inference::CudaSharedMemoryStatusResponse
- inference::CudaSharedMemoryUnregisterRequest
- inference::CudaSharedMemoryUnregisterResponse
- inference::InferBatchStatistics
- inference::InferParameter
- inference::InferStatistics
- inference::InferTensorContents
- inference::LogSettingsRequest
- inference::LogSettingsResponse
- inference::ModelConfig
- inference::ModelConfigRequest
- inference::ModelConfigResponse
- inference::ModelDynamicBatching
- inference::ModelEnsembling
- inference::ModelInferRequest
- inference::ModelInferResponse
- inference::ModelInput
- inference::ModelInstanceGroup
- inference::ModelMetadataRequest
- inference::ModelMetadataResponse
- inference::ModelOperations
- inference::ModelOptimizationPolicy
- inference::ModelOutput
- inference::ModelParameter
- inference::ModelQueuePolicy
- inference::ModelRateLimiter
- inference::ModelReadyRequest
- inference::ModelReadyResponse
- inference::ModelRepositoryAgents
- inference::ModelRepositoryParameter
- inference::ModelResponseCache
- inference::ModelSequenceBatching
- inference::ModelStatistics
- inference::ModelStatisticsRequest
- inference::ModelStatisticsResponse
- inference::ModelStreamInferResponse
- inference::ModelTensorReshape
- inference::ModelTransactionPolicy
- inference::ModelVersionPolicy
- inference::ModelWarmup
- inference::RepositoryIndexRequest
- inference::RepositoryIndexResponse
- inference::RepositoryModelLoadRequest
- inference::RepositoryModelLoadResponse
- inference::RepositoryModelUnloadRequest
- inference::RepositoryModelUnloadResponse
- inference::ServerLiveRequest
- inference::ServerLiveResponse
- inference::ServerMetadataRequest
- inference::ServerMetadataResponse
- inference::ServerReadyRequest
- inference::ServerReadyResponse
- inference::StatisticDuration
- inference::SystemSharedMemoryRegisterRequest
- inference::SystemSharedMemoryRegisterResponse
- inference::SystemSharedMemoryStatusRequest
- inference::SystemSharedMemoryStatusResponse
- inference::SystemSharedMemoryUnregisterRequest
- inference::SystemSharedMemoryUnregisterResponse
- inference::TraceSettingRequest
- inference::TraceSettingResponse
- inference::cuda_shared_memory_status_response::RegionStatus
- inference::grpc_inference_service_client::GrpcInferenceServiceClient
- inference::log_settings_request::SettingValue
- inference::log_settings_response::SettingValue
- inference::model_ensembling::Step
- inference::model_infer_request::InferInputTensor
- inference::model_infer_request::InferRequestedOutputTensor
- inference::model_infer_response::InferOutputTensor
- inference::model_instance_group::SecondaryDevice
- inference::model_metadata_response::TensorMetadata
- inference::model_optimization_policy::Cuda
- inference::model_optimization_policy::ExecutionAccelerators
- inference::model_optimization_policy::Graph
- inference::model_optimization_policy::PinnedMemoryBuffer
- inference::model_optimization_policy::cuda::GraphSpec
- inference::model_optimization_policy::cuda::graph_spec::LowerBound
- inference::model_optimization_policy::cuda::graph_spec::Shape
- inference::model_optimization_policy::execution_accelerators::Accelerator
- inference::model_rate_limiter::Resource
- inference::model_repository_agents::Agent
- inference::model_sequence_batching::Control
- inference::model_sequence_batching::ControlInput
- inference::model_sequence_batching::InitialState
- inference::model_sequence_batching::State
- inference::model_sequence_batching::StrategyDirect
- inference::model_sequence_batching::StrategyOldest
- inference::model_version_policy::All
- inference::model_version_policy::Latest
- inference::model_version_policy::Specific
- inference::model_warmup::Input
- inference::repository_index_response::ModelIndex
- inference::system_shared_memory_status_response::RegionStatus
- inference::trace_setting_request::SettingValue
- inference::trace_setting_response::SettingValue
Enums
- error::ModelError
- error::TritonClientError
- inference::DataType
- inference::batch_input::Kind
- inference::batch_output::Kind
- inference::infer_parameter::ParameterChoice
- inference::log_settings_request::setting_value::ParameterChoice
- inference::log_settings_response::setting_value::ParameterChoice
- inference::model_config::SchedulingChoice
- inference::model_input::Format
- inference::model_instance_group::Kind
- inference::model_instance_group::secondary_device::SecondaryDeviceKind
- inference::model_optimization_policy::ModelPriority
- inference::model_queue_policy::TimeoutAction
- inference::model_repository_parameter::ParameterChoice
- inference::model_sequence_batching::StrategyChoice
- inference::model_sequence_batching::control::Kind
- inference::model_sequence_batching::initial_state::StateData
- inference::model_version_policy::PolicyChoice
- inference::model_warmup::input::InputDataType