'tensor.cast' op operand type 'tensor<64x64x112x112xf32>' and result type 'tensor<1x64x112x112xf32>' are cast incompatible : Mul with broadcast + reshape

[pravg-amd]

For the below IR,

module {
  func.func @inception_v2(%arg0: !torch.vtensor<[1,64,112,112],f32>, %arg1: !torch.vtensor<[64],f32>) ->  !torch.vtensor<[1,64,112,112],f32>  attributes {torch.onnx_meta.ir_version = 3 : si64, torch.onnx_meta.opset_version = 21 : si64, torch.onnx_meta.producer_name = "onnx-caffe2", torch.onnx_meta.producer_version = ""} {
    %0 = torch.operator "onnx.Constant"() {torch.onnx.value = dense<[1, 2, 3]> : tensor<3xsi64>} : () -> !torch.vtensor<[3],si64>
    %1 = torch.operator "onnx.Unsqueeze"(%arg1, %0) : (!torch.vtensor<[64],f32>, !torch.vtensor<[3],si64>) -> !torch.vtensor<[64,1,1,1],f32>
    %2 = torch.operator "onnx.Mul"(%arg0, %1) : (!torch.vtensor<[1,64,112,112],f32>, !torch.vtensor<[64,1,1,1],f32>) -> !torch.vtensor<[1,64,112,112],f32>
    return %2 : !torch.vtensor<[1,64,112,112],f32>
  }
}

Getting error as

model_torch_onnx.mlir:5:10: error: 'tensor.cast' op operand type 'tensor<64x64x112x112xf32>' and result type 'tensor<1x64x112x112xf32>' are cast incompatible
    %2 = torch.operator "onnx.Mul"(%arg0, %1) : (!torch.vtensor<[1,64,112,112],f32>, !torch.vtensor<[64,1,1,1],f32>) -> !torch.vtensor<[1,64,112,112],f32>

Command

iree-compile --iree-hal-target-backends=llvm-cpu --iree-llvmcpu-target-cpu=host -o test.vmfb model_torch_onnx.mlir

Model Impacted:
inception-v2-6