Looks interesting! Is there any intuition for why this should be the case? Did you discover it via that intuition, or just random experimentation?
A note, your install script appears to still have a placeholder at the "apply patch" step. A suggestion, might be more user-friendly to fork llama.cpp and then include that as a git submodule rather than make it a "git clone and apply patch" step.
A further note, everyone and their dog has a different local python set-up, might be nice to let people separate the llama.cpp stuff from the python stuff rather than bake in a dependence on homebrew python.
A note, your install script appears to still have a placeholder at the "apply patch" step. A suggestion, might be more user-friendly to fork llama.cpp and then include that as a git submodule rather than make it a "git clone and apply patch" step.
A further note, everyone and their dog has a different local python set-up, might be nice to let people separate the llama.cpp stuff from the python stuff rather than bake in a dependence on homebrew python.