t-vi opened a new pull request #5763: URL: https://github.com/apache/incubator-tvm/pull/5763
Previously, the PyTorch frontend approximated gelu with fastgelu. To provide a more faithful conversion, we implement gelu instead. We also tighten the numerical comparisons between PyTorch and TVM-from-PyTorch to 1e-5. The object detection models need an increased tolerance of 1e-4 to pass. I do both in one go because the new gelu necessitates and is tested by the tightened testing tolerance. I had to throw in a few fixes for missing conversions (probably due to working with very new PyTorch). ---------------------------------------------------------------- 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]
