iris-ai 6ed896f1e1 Record the install trap behind a llama.cpp build that never answers ...

`llama-server` is a 16 KB launcher against `libllama-server-impl.so`, so a
build installed without a working runpath dies at exec and reaches the phone
as a model that never became ready. `GNUInstallDirs` picks `lib64` on some
distributions while the recorded runpath says `lib`, which is how the two
flags come apart.

2026-09-21 02:05:24 -04:00

..

ai-app-rigs

Record the install trap behind a llama.cpp build that never answers

2026-09-21 02:05:24 -04:00