Thrsu opened a new issue, #15722: URL: https://github.com/apache/tvm/issues/15722
I encountered this TVMError when attempting to load an [ONNX model](https://github.com/Thrsu/onnx_model/blob/main/Add.onnx) containing the Add operator using TVM's relax module. It seems that relax.add cannot handle. But the unittest [test_frontend_onnx.py](https://github.com/apache/tvm/blob/unity/tests/python/relax/test_frontend_onnx.py) is passed. So I am puzzled. And I noticed that there is a similar issue reported in the TVM repository: #14437 However, the suggested solution mentioned in that issue did not resolve the problem in my case. ### Environment - branch: unity - tvm: v0.14.dev0-595-gfa0d35b - onnx: 1.14.0 ### Steps to reproduce ```python import onnx import tvm from tvm import relax from tvm.relax.frontend.onnx import from_onnx onnx_model_path = "Add.onnx" model = onnx.load(onnx_model_path) tvm_model = from_onnx(model, opset=18, keep_params_in_input=True) tvm_model = relax.transform.LegalizeOps()(tvm_model) ex = relax.build(tvm_model, target="llvm") vm = relax.VirtualMachine(ex, tvm.cpu()) ``` ### Triage * needs-triage -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
