❓ [Question] How to specific aten operators must be run by LibTorch in C++?

❓ Question

When I compile the SwinTransformer model using Torch-TensorRT, an error appears:

terminate called after throwing an instance of 'c10::Error'
  what():  0 INTERNAL ASSERT FAILED at "../torch/csrc/jit/ir/alias_analysis.cpp":615, please report a bug to PyTorch. We don't have an op for aten::floor_divide but it isn't a special case.  Argument types: int, int, 

Candidates:
        aten::floor_divide(Tensor self, Tensor other) -> Tensor
        aten::floor_divide.Scalar(Tensor self, Scalar other) -> Tensor
        aten::floor_divide.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)
        aten::floor_divide.Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!)

I checked out this link, This error is because torch-trt dont support % op.

Fine, I can select to run floor_divide using LibTorch.

torchtrt::ts::CompileSpec compile_settings({ input });
compile_settings.enabled_precisions.insert(build_type);
compile_settings.workspace_size = _1_GB;
compile_settings.truncate_long_and_double = true;
compile_settings.num_avg_timing_iters = 1;
compile_settings.torch_executed_ops.push_back("aten::floor_divide");  // here
torchtrt::ts::compile(model, compile_settings)

It's strange that the setting does not take effect. This error still persists.

What can I do about this mistake?

Furthermore, How to specific aten operators must be run by LibTorch in C++?

Environment

Build information about Torch-TensorRT can be found by turning on debug messages

• PyTorch Version (e.g., 1.0):2.2.1
• CPU Architecture:x86
• OS (e.g., Linux):ubuntu22.04
• How you installed PyTorch (conda, pip, libtorch, source):
• Build command you used (if compiling from source):
• Are you using local sources or building from archives:
• Python version:
• CUDA version:12.2
• GPU models and configuration:
• Any other relevant information: