altanh opened a new pull request #7604: URL: https://github.com/apache/tvm/pull/7604
Previously, if a graph module returned nested tuples (which end up being flattened per #6809), the GraphExecutor would not unflatten the result and instead naively returned only the first `k` of the flattened outputs (where `k = original top-level tuple size`). This PR fixes the output behavior of GraphExecutor to be the same as the VMExecutor ,by returning the outputs unflattened into nested lists respecting the original return type structure. cc @masahi @jroesch I'm not super happy with the unflattening code, let me know if there's an easier/cleaner approach. ---------------------------------------------------------------- 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]
