Struct Client

pub struct Client {
    pub inner: GrpcInferenceServiceClient<InterceptedService<Channel, AuthInterceptor>>,
}

Triton Client

Fields

inner: GrpcInferenceServiceClient<InterceptedService<Channel, AuthInterceptor>>

Raw grpc client interfaces automatically generated by tonic

Should not necessary to use this interface directly in most cases

Implementations

impl Client

pub async fn new( url: impl TryInto<Uri, Error = InvalidUri>, access_token: Option<String>, ) -> Result<Self, Error>

Create a new triton client for the given url.

pub async fn server_live(&self) -> Result<ServerLiveResponse, Error>

Check liveness of the inference server.

pub async fn server_ready(&self) -> Result<ServerReadyResponse, Error>

Check readiness of the inference server.

pub async fn model_ready( &self, req: ModelReadyRequest, ) -> Result<ModelReadyResponse, Error>

Check readiness of a model in the inference server.

pub async fn server_metadata(&self) -> Result<ServerMetadataResponse, Error>

Get server metadata.

pub async fn model_metadata( &self, req: ModelMetadataRequest, ) -> Result<ModelMetadataResponse, Error>

Get model metadata.

pub async fn model_infer( &self, req: ModelInferRequest, ) -> Result<ModelInferResponse, Error>

Perform inference using a specific model.

pub async fn model_config( &self, req: ModelConfigRequest, ) -> Result<ModelConfigResponse, Error>

Get model configuration.

pub async fn model_statistics( &self, req: ModelStatisticsRequest, ) -> Result<ModelStatisticsResponse, Error>

Get the cumulative inference statistics for a model.

pub async fn repository_index( &self, req: RepositoryIndexRequest, ) -> Result<RepositoryIndexResponse, Error>

Get the index of model repository contents.

pub async fn repository_model_load( &self, req: RepositoryModelLoadRequest, ) -> Result<RepositoryModelLoadResponse, Error>

Load or reload a model from a repository.

pub async fn repository_model_unload( &self, req: RepositoryModelUnloadRequest, ) -> Result<RepositoryModelUnloadResponse, Error>

Unload a model.

pub async fn system_shared_memory_status( &self, req: SystemSharedMemoryStatusRequest, ) -> Result<SystemSharedMemoryStatusResponse, Error>

Get the status of all registered system-shared-memory regions.

pub async fn system_shared_memory_register( &self, req: SystemSharedMemoryRegisterRequest, ) -> Result<SystemSharedMemoryRegisterResponse, Error>

Register a system-shared-memory region.

pub async fn system_shared_memory_unregister( &self, req: SystemSharedMemoryUnregisterRequest, ) -> Result<SystemSharedMemoryUnregisterResponse, Error>

Unregister a system-shared-memory region.

pub async fn cuda_shared_memory_status( &self, req: CudaSharedMemoryStatusRequest, ) -> Result<CudaSharedMemoryStatusResponse, Error>

Get the status of all registered CUDA-shared-memory regions.

pub async fn cuda_shared_memory_register( &self, req: CudaSharedMemoryRegisterRequest, ) -> Result<CudaSharedMemoryRegisterResponse, Error>

Register a CUDA-shared-memory region.

pub async fn cuda_shared_memory_unregister( &self, req: CudaSharedMemoryUnregisterRequest, ) -> Result<CudaSharedMemoryUnregisterResponse, Error>

Unregister a CUDA-shared-memory region.

pub async fn trace_setting( &self, req: TraceSettingRequest, ) -> Result<TraceSettingResponse, Error>

Update and get the trace setting of the Triton server.

Trait Implementations

impl Clone for Client

fn clone(&self) -> Client

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Client

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.