lhutton1 opened a new pull request, #11091: URL: https://github.com/apache/tvm/pull/11091
The sequence of calls produced by the AOT executor codegen is arbitrary, especially in the presence of 'branchy' networks. This makes it difficult to analyze memory usage for each call. By running the ToANormalForm pass to insert a series of let bindings before the lowering and codegen stages, we can establish an ordering for the evaluation of the external calls, thus allowing reliable analysis of memory usage. cc @manupa-arm @Mousius @areusch @mbs-octoml @ashutosh-arm @ekalda @NicolaLancellotti -- 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]
