coffezhou commented on issue #18585: URL: https://github.com/apache/tvm/issues/18585#issuecomment-3688963461
Hi, I tested TVM with some models and found some issues (#18595, #18602, and #18603) like this one. Since the problem appears in different operators (Hardmax, ArgMax, ArgMin, and LayerNormalization), I reported them separately. Maybe the reported issues are duplicated for this one. Sorry for submitting these issues before reading this. In each issue, I provided testcase including onnx model, inputs, and test script. I will try the patch proposed by @yunho-c and report the results. -- 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]
