Haoran-Young opened a new pull request #6022: URL: https://github.com/apache/incubator-tvm/pull/6022
Some users adopt ONNX to convert and save their trained models. But some of the models are big, which have sizes larger than 2GB. In these cases, ONNX cannot save these big models successfully. Recently, developers of ONNX have made some updates on ONNX so that ONNX can save, load, check big models. I note that TVM cannot yet support compiling big ONNX models because TVM fails to check big ONNX models. I have made minor modifications to the source codes so that TVM can support checking and compiling big ONNX models. @adityaatluri @liangfu @zhiics Could you please have a look on 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. For queries about this service, please contact Infrastructure at: [email protected]
