Struct TfLiteQnnDelegateGpuBackendOptions¶
Defined in File QnnTFLiteDelegate.h
Struct Documentation¶
-
struct TfLiteQnnDelegateGpuBackendOptions¶
Specifies the backend options for the GPU backend. To be used when selecting TfLiteQnnDelegateBackendType::kGpuBackend for the TfLiteQnnDelegateOptions::backend_type.
Public Members
-
TfLiteQnnDelegateGpuPrecision precision¶
The default precision is half float for the best performance.
-
TfLiteQnnDelegateGpuPerformanceMode performance_mode¶
The default performance mode sets high.
-
const char *kernel_repo_dir¶
The QNN GPU backend supports on-disk kernel persistence strategies where compiled GPU kernel binaries are cached to disk and can be shared across models having the same kernels and improve warm init times significantly.
-
TfLiteQnnDelegateGpuPrecision precision¶