Switch back to subprocessing for llama.cpp

This should resolve a number of memory leak and stability defects by allowing
us to isolate llama.cpp in a separate process and shutdown when idle, and
gracefully restart if it has problems.  This also serves as a first step to be
able to run multiple copies to support multiple models concurrently.

llm/ext_server/server.cpp

@@ -2768,7 +2768,7 @@ inline void signal_handler(int signal) {
     shutdown_handler(signal);
 }
 
-int _main(int argc, char **argv)
+int main(int argc, char **argv)
 {
 #if SERVER_VERBOSE != 1
     log_disable();