for (int i = 0; i < num_dims; ++i) {
    dimvec[i] = static_cast<int64_t>(dims[i]);
  }

  // TODO(apassos) do we need to wrap the deallocator here to make sure to sync
  // the device?
  TF_ManagedBuffer* buf =
      new TF_ManagedBuffer(data, len, deallocator, deallocator_arg,
                           /*owns_memory=*/false);

  tensorflow::Tensor t(static_cast<tensorflow::DataType>(dtype),