Bundle only llama.cpp from llamadart

Translation runs GGUF models on llama.cpp. llamadart 0.8.20+ also bundles the
LiteRT-LM runtime, whose iOS GemmaModelConstraintProvider.framework requires
iOS 26.4, so App Store Connect rejects 16.4 builds (ITMS-90208).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
ahalekellyandClaude Opus 5.5 committed 2026-11-01 14:39:22 -08:00
1 parent 78f426e979
commit c8607804a3
1 file changed
+2
+2
View File
@@ -90,6 +90,8 @@ dependencies:
hooks:
user_defines:
llamadart:
# Translation uses llama.cpp. LiteRT-LM is unused and requires iOS 26.4.
llamadart_native_runtimes: [llama_cpp]
llamadart_native_backends:
platforms:
android-arm64: