resize_inputs: Tensor = symbol([1, 3, "h", "w"], dtype="int32", device="cpu")
resize_outputs = self.resize(resize_inputs.to(self.dtype, self.device))  # (float32, cuda)
resize_graph: FlowGraph = trace_from(resize_outputs, resize_inputs)

resize_graph.build()

DLL void hidet_launch_0(float * __restrict__ x, float * __restrict__ y) {
  cudaMemcpyAsync(y, x, (4 * ((3 * h) * w)), cudaMemcpyHostToDevice, (cudaStream_t)get_cuda_stream());
}