Lunderberg opened a new pull request, #14564: URL: https://github.com/apache/tvm/pull/14564
Because LLVM's optimizations assume that the generated module is valid, validation should be done before optimization, rather than after. This has the additional benefit of providing error messages from LLVM that more closely relate to the TVM-generated LLVM IR, rather than the optimized LLVM IR. -- 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]
