Skip to main content

Crate baracuda_tensorrt_sys

Crate baracuda_tensorrt_sys 

Source
Expand description

Raw FFI + dynamic loader for NVIDIA TensorRT (C API surface).

TensorRT’s native public API is C++; NVIDIA ships a partial C-ABI surface suitable for language bindings in NvInferRuntimeCAPI.h (TRT 10+). This crate wraps that surface for runtime deserialization and inference. The builder side of TensorRT remains C++-only; use the TRT trtexec tool or the Python bindings to produce serialized engines, then load them here.

Structs§

TensorRt
trtDims_t
trtStatus_t
TensorRT C API returns bool (0/1) or int32_t status codes depending on the function. We provide a thin trtStatus_t newtype for the error-reporting subset so it implements CudaStatus.

Enums§

trtDataType_t
trtExecutionContextAllocationStrategy_t
trtSeverity_t
trtTensorIOMode_t

Constants§

TRT_MAX_DIMS
Analog of nvinfer1::Dims — up to 8 dimensions.

Functions§

tensorrt

Type Aliases§

PFN_contextEnqueueV3
PFN_contextGetTensorAddress
PFN_contextGetTensorShape
PFN_contextSetInputShape
PFN_contextSetTensorAddress
PFN_createInferRuntime
PFN_deserializeCudaEngine
PFN_destroyCudaEngine
PFN_destroyExecutionContext
PFN_destroyInferRuntime
PFN_engineCreateExecutionContext
PFN_engineCreateExecutionContextWithStrategy
PFN_engineGetIOTensorName
PFN_engineGetName
PFN_engineGetNbIOTensors
PFN_engineGetNbOptimizationProfiles
PFN_engineGetTensorBytesPerComponent
PFN_engineGetTensorDataType
PFN_engineGetTensorIOMode
PFN_engineGetTensorShape
PFN_engineSerialize
PFN_getInferLibVersion
PFN_hostMemoryData
PFN_hostMemoryDestroy
PFN_hostMemorySize
trtICudaEngine_t
trtIExecutionContext_t
trtIHostMemory_t
trtILogger_t
trtIPluginRegistry_t
trtIRuntime_t
trtLogCallback
Logger callback signature (matches nvinfer1::ILogger::log).