MargaretQian opened a new pull request, #10985: URL: https://github.com/apache/tvm/pull/10985
Looking at the onnx op documentation, it appears that the axes for unsqueeze are expected to be applied in sorted order: https://github.com/onnx/onnx/blob/main/docs/Operators.md#Unsqueeze Also, although tests are a bit slow, they're taking <5 min when I tried locally for non-llvm targets (cuda, opencl), so I'm uncommenting them. -- 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]
