RandomNormalLike not supported

[col-in-coding]

Description

I got an error when parse onnx to tensorrt. Onnx has only one layer RandomNormalLike. Based on docs RandomNormalLike should be supported, so I'm wondering if there is any mistake I made.

In node 0 (importFallbackPluginImporter): UNSUPPORTED_NODE: Assertion failed: creator && "Plugin not found, are the plugin name, version, and namespace correct?"

Python code:

class MyModel(torch.nn.Module):
    def __init__(self) -> None:
        super().__init__()
    
    def forward(self, x):
        device = x.device
        return torch.randn_like(x, device=device)

onnx_path = "test.onnx"
x = torch.rand(3, 256, 256).type(torch.float32)
torch.onnx.export(torch_model,
                      x,
                      onnx_path,
                      input_names=["x"],
                      output_names=["output"],
                      opset_version=12,
                      export_params=True)

Environment

TensorRT Version: 8.4.3.1 ONNX-TensorRT Version / Branch: don't known, along with tensorrt 8.4.3.1 tar file GPU Type: A100 Nvidia Driver Version: 470.57.02 CUDA Version: 11.4 CUDNN Version: Operating System + Version: Python Version (if applicable): 3.8.5 TensorFlow + TF2ONNX Version (if applicable): PyTorch Version (if applicable): 1.7.1 Baremetal or Container (if container which image + tag):

Relevant Files

Steps To Reproduce