jwfromm opened a new pull request #8475:
URL: https://github.com/apache/tvm/pull/8475


   A user recently noted that there are some issues importing some DLRM models 
generated by Pytorch in[ this 
thread](https://discuss.tvm.apache.org/t/dlrm-onnx-strided-slice-in-loop-issues/10483).
 After investigating, I found that the problem is that Pytorch is generating 
loop nodes without proper output shape information, which causes us to use 
improper variable shapes. To fix this, we can instead to type inference on the 
loop body to figure out output shapes on our own. This should be more robust in 
general.
   
   I've added a test case with a malformed loop node to confirm this fix works. 
I also removed an old warning that has since been fixed.


-- 
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]


Reply via email to