Add XNN Pack toggle switch for ONNX inference acceleration (#155)

* Initial plan

* Add XNN Pack switch for ONNX inference acceleration

Co-authored-by: xkeyC <39891083+xkeyC@users.noreply.github.com>

* Refactor Rust ONNX session creation to reduce code duplication

Co-authored-by: xkeyC <39891083+xkeyC@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: xkeyC <39891083+xkeyC@users.noreply.github.com>
This commit is contained in:
Copilot
2025-11-28 21:23:31 +08:00
committed by GitHub
parent db024f19bd
commit db89100402
26 changed files with 197 additions and 74 deletions

View File

@@ -82,7 +82,7 @@ final class AppGlobalModelProvider
}
}
String _$appGlobalModelHash() => r'51f72c5d8538e2a4f11d256802b1a1f2e04d03be';
String _$appGlobalModelHash() => r'9729c3ffb891e5899abbb3dc7d2d25ef13a442e7';
abstract class _$AppGlobalModel extends $Notifier<AppGlobalState> {
AppGlobalState build();