TVM generated kernels not being detected by Nvidia Nsight Compute

I am trying to evaluate performance of the following model: U-Net for brain MRI | PyTorch . I am running this model using TVM. The model is running fine, but when I try to evaluate the model using Nsight Compute , all the CUDA kernels get detected except the ones that are generated by TVM.

Is anyone facing the same issue or knows how to fix this issue?