Part 2 of the series, covers export, AOTInductor for getting runnable models on the server and ExecuTorch for runnable models on edge device (phones, wearables etc). There are a number of good examples from real world experience in there of how to use these tools as well. As usual I learned about something I didn’t know existed, in this case it was intermediate tensor logging in AOTI:
AOTInductor has an option to add dumps of intermediate tensor values in the compiled C++ code. This is good for determining, e.g., the first time where a NaN shows up, in case you are suspecting a miscompilation.