Shirley4042 opened a new issue, #20049:
URL: https://github.com/apache/tvm/issues/20049

   ## Expected behavior
   
   I am trying to import NVIDIA BEVFusion ONNX models into TVM.
   
   
[testcase.zip](https://github.com/user-attachments/files/30374145/testcase.zip)
   
   The ONNX models contain two custom sparse operators:
   
   -   SparseConvolution
   -   ScatterDense
   
   I expect the TVM ONNX frontend to either:
   
   1.  Directly import these operators into corresponding Relax operators,
       or
   2.  Provide a recommended extension mechanism for lowering these
       operators into TVM-compatible representations.
   
   ## Actual behavior
   
   Importing the ONNX models fails because the TVM ONNX frontend does not
   recognize these operators.
   
   Error:
   
       OpNotImplemented:
       The following operators are not supported for frontend ONNX:
       SparseConvolution, ScatterDense
   
   ## Environment
   
   -   TVM: TVM v0.25.dev0
   -   OS: Ubuntu 22.04
   -   Python: 3.11
   
   ## Model information
   
   Example:
   
       testcase
   
   
[testcase.zip](https://github.com/user-attachments/files/30374155/testcase.zip)
   
   .onnx
   
   Graph structure:
   
       Input
        |
       SparseConvolution x21
        |
       Add
        |
       Relu
        |
       ScatterDense
        |
       Output
   
   The operators are custom ONNX operators generated by NVIDIA sparse
   convolution implementation.
   
   ## Questions
   
   1.  Should SparseConvolution and ScatterDense be added as new Relax
       operators?
   
   2.  Does TVM have an existing recommended extension mechanism for
       importing non-standard ONNX sparse operators?
   
   
   


-- 
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]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to