llama : more metal-friendly KV cache PAD

llama.cpp

@@ -11508,7 +11508,7 @@ static int llama_decode_internal(
                 // a heuristic, to avoid attending the full cache if it is not yet utilized
                 // after enough generations, the benefit from this heuristic disappears
                 // if we start defragmenting the cache, the benefit from this will be more important
-                kv_self.n = std::min(kv_self.size, std::max(256u, GGML_PAD(llama_kv_cache_cell_max(kv_self), 256)));
+                kv_self.n = std::min(kv_self.size, std::max(128u, GGML_PAD(llama_kv_cache_cell_max(kv_self), 128)));
                 //kv_self.n = llama_kv_cache_cell_max(kv_self);
             }
         }