Warning: llama.cpp --lazy-mode default changed to auto - large tables may stay on disk

With b10726, the default --lazy-mode change keeps the 51B-parameter PLE n-gram embedding table of Qwen 3.8 Flash Next on disk: it is mmap'd and its rows are read on demand during inference, even with --load-mode none. It is no longer loaded into RAM unless --lazy-mode off is passed. This change resu