metal : reusing llama.cpp logging (#3152)

* metal : reusing llama.cpp logging

* cmake : build fix

* metal : logging callback

* metal : logging va_args memory fix

* metal : minor cleanup

* metal : setting function like logging macro to capital letters

* llama.cpp : trailing whitespace fix

* ggml : log level enum used by llama

* Makefile : cleanup ggml-metal recipe

* ggml : ggml_log_callback typedef

* ggml : minor

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

ggml-metal.h

@@ -19,6 +19,8 @@
 
 #pragma once
 
+#include "ggml.h"
+
 #include <stddef.h>
 #include <stdbool.h>
 
@@ -33,6 +35,8 @@ struct ggml_cgraph;
 extern "C" {
 #endif
 
+void ggml_metal_log_set_callback(ggml_log_callback log_callback, void * user_data);
+
 struct ggml_metal_context;
 
 // number of command buffers to use