zhiics opened a new pull request #6487: URL: https://github.com/apache/incubator-tvm/pull/6487
This PR makes saving and loading tensor size consistent for DLTensor serialization. This somehow was triggered by recent dynamic operator changes but only caught in some large models like TF SSD and PT MaskRCNN, etc. cc @tqchen @kevinthesun @icemelon9 ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected]
