List<OptimizationProfileConfig> OptimizationProfiles { get; set; } |
Gets or sets optimization profiles for dynamic shapes. |
List<string> CustomPluginPaths { get; set; } |
Gets or sets custom plugin library paths. |
TensorRTPrecision Precision { get; set; } |
Gets or sets the inference precision mode (default: FP32). |
bool CleanupIntermediateFiles { get; set; } |
Gets or sets whether to cleanup intermediate files (ONNX, etc.) (default: true). |
bool EnableCudaGraphs { get; set; } |
Gets or sets whether to enable CUDA graph capture (default: false). |
bool EnableDLA { get; set; } |
Gets or sets whether to enable Deep Learning Accelerator (DLA) on Jetson devices. |
bool EnableDynamicShapes { get; set; } |
Gets or sets whether to enable dynamic shapes (default: false). |
bool EnableMultiStream { get; set; } |
Gets or sets whether to use multi-stream execution (default: false). |
bool EnableProfiling { get; set; } |
Gets or sets whether to enable profiling (default: false). |
bool StrictTypeConstraints { get; set; } |
Gets or sets whether to enable strict type constraints (default: false). |
int BuilderOptimizationLevel { get; set; } |
Gets or sets the builder optimization level (0-5, higher is more optimization). |
int DLACore { get; set; } |
Gets or sets the DLA core to use when EnableDLA is true (-1 = disabled, 0+ = specific core). |
int DeviceId { get; set; } |
Gets or sets the GPU device ID to use (default: 0). |
int MaxBatchSize { get; set; } |
Gets or sets the maximum batch size for inference (default: 1). |
int NumStreams { get; set; } |
Gets or sets the number of streams for multi-stream execution (default: 2). |
long MaxWorkspaceSize { get; set; } |
Gets or sets the maximum workspace size in bytes for TensorRT (default: 1GB). |
string CalibrationDataPath { get; set; } |
Gets or sets the path to calibration data for INT8 quantization. |
string EngineCachePath { get; set; } |
Gets or sets the engine cache path for faster reloading. |