llama.cpp

165caaf5 - metal: use shared buffers on eGPU (#17866)

metal: use shared buffers on eGPU (#17866) * metal: use shared buffers on eGPU With #15906, I noticed on important regression when using metal backend on eGPU. This commit restore the previous behavior and add an option to force its activation. * metal: use shared buffers on eGPU * metal: use shared buffers on eGPU