As we described on the title, the model that I have built completely works on iPhone 15 / A16 Bionic, on the other hand it does not run on iPhone 16 / A18 chip with the following error message. E5RT encountered an STL exception. msg = MILCompilerForANE error: failed to compile ANE model using ANEF. Error=_ANECompiler : ANECCompile() FAILED. E5RT: MILCompilerForANE error: failed to compile ANE model using ANEF. Error=_ANECompiler : ANECCompile() FAILED (11) It consumes 1.5 ~ 1.6 GB RAM on the loading the model, then the consumption is decreased to less than 100MB on the both of iPhone 15 and 16. After that, only on iPhone 16, the above error is shown on the Xcode log, the memory consumption is surged to 5 to 6GB, and the system kills the app. It works well only on iPhone 15. This model is built with the Core ML tools. Until now, I have tried the target iOS 16 to 18 and the compute units of CPU_AND_NE and ALL. But any ways have not solved this issue. Eventually, what kindof fix should I do? minimum_deployment_target = ct.target.iOS18 compute_units = ct.ComputeUnit.ALL compute_precision = ct.precision.FLOAT16

This "silently" indicates the following. It seems impossible to investigate the causes of the crash. The number of crashes on the organizer does not contain this. The crash log is not sent at all. The crash log is not left on the device. The number of crashes on "App Store Connect > Analytics > Metrics > Crashes" does not contain this. Currently, we understand the tendencies of this crash are as follows. Higher resolution devices. Older models. Therefore, we consider that the crashes are relevant to the memory consumption. However, we are not assured of that because of the following causes. There are no crash logs. The specific numbers of the memory limitation are undocumented publicly. The keyboard app developers consider it an open secret, and the threshold value is based on various hypotheses. The questions are as follows. Is there a way to identify the cause? Are there the same or similar reports? Is there an approach to solve this crash?