t-vi opened a new pull request #5911: URL: https://github.com/apache/incubator-tvm/pull/5911
PyTorch implements vanilla Linear (without broadcasting) though a function addmm that accepts scalar multipliers. These multipliers are constant 1 typically, so this patch skips the multiplication for this common case. @siju-samuel @masahi ---------------------------------------------------------------- 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]
