Function torch_tensorrt::executorch_backend::select_profile

• Defined in File OptimizationProfileSelection.h

Function Documentation

inline ProfileSelection torch_tensorrt::executorch_backend::select_profile(const ProfileTable &table, ProfileRequest request, int32_t index, const std::vector<nvinfer1::Dims> &input_dims, int32_t &selected)

Resolves one thread’s profile request against one engine.

Parameters:

• table – The engine’s profile bounds and currently loaded profile.

• request – What the calling thread asked for.

• index – The pinned profile index; read only for ProfileRequest::kPinned.

• input_dims – Runtime shape of each input, in binding order.

• selected – [out] The profile to run, written only when the result allows execution to continue (ProfileSelection::kOk or ProfileSelection::kPinIgnoredSingleProfile).

Returns:

What the caller should do, and which message it should print.