leandron commented on PR #16653: URL: https://github.com/apache/tvm/pull/16653#issuecomment-1985385711
> The pull request for supporting ONNX quantized models was merged earlier than the PR for supporting PaddlePaddle quantized models. Since we allow for errors in ONNX quantized models in TVM, why can't we allow for the same level of error in PaddlePaddle quantized models in TVM? Sure, I understand your point. I agree with this approach, please add tests for the PaddlePaddle path offloading softmax to CMSIS-NN that contain an error margin for the expected numerical discrepancy. Please do that as part of this PR. -- 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]
