The kernel or script crashed when loading ONNX by tvm

#1

I try to use tvmc.load() to load my .onnx file

model = tvmc.load(onnx_model_file)

but the script return error

(miniforge3) jianhuama@mbp-1h7q6d % python convert_pytorch_to_c.py scripted_model.pt 
/Users/jianhuama/.pyenv/versions/miniforge3/envs/*/lib/python3.8/site-packages/torch/onnx/utils.py:847: UserWarning: no signature found for <torch.ScriptMethod object at 0x16a466d60>, skipping _decide_input_format
  warnings.warn(f"{e}, skipping _decide_input_format")
Model Hash: 867b46e960693f5a45eb86ae26ac681025c9a03851bc2799c59f2745b9b5effd
zsh: trace trap  python convert_pytorch_to_c.py scripted_model_.pt

I try to create a new instance to test in jupyter notebook:

import torch
import torch.nn as nn
import onnx
import tvm
from tvm import relay
# Define a simple model in PyTorch
class SimpleModel(nn.Module):
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.linear = nn.Linear(10, 1)

    def forward(self, x):
        return self.linear(x)

# Create a model instance and a dummy input
simple_model = SimpleModel()
x = torch.randn(1, 10)

# Export the model to ONNX
torch.onnx.export(simple_model, x, "simple_model.onnx")

# Load the ONNX model
onnx_model = onnx.load("simple_model.onnx")
# Convert the ONNX model to a Relay computation graph
shape_dict = {"onnx::Gemm_0": (1, 10)}
relay_model, params = relay.frontend.from_onnx(onnx_model, shape_dict)

print(relay_model)

return error:

The Kernel crashed while executing code in the the current cell or a previous cell. Please review the code in the cell(s) to identify a possible cause of the failure. Click here for more info. View Jupyter log for further details.

Looks like my tvm always crash when loading onnx file. can someone have any idea? My lib: tvm == 0.14.0 onnx == 1.15.0

I