Implement server mode.

This new mode works by first loading the model then listening for TCP
connections on a port. When a connection is received, arguments will be
parsed using a simple protocol:

- First the number of arguments will be read followed by a newline
  character.
- Then each argument will be read, separated by the 0 byte.
- With this we build an argument vector, similar to what is passed to
  the program entry point. We pass this to gpt_params_parse.

Finally `run` will be executed with the input/output streams connected
to the socket.

Signed-off-by: Thiago Padilha <thiago@padilha.cc>

main.cpp

@@ -1,5 +1,6 @@
 #include "run.h"
 #include "ggml.h"
+#include "tcp_server.h"
 
 #include <iostream>
 
@@ -125,5 +126,11 @@ int main(int argc, char ** argv) {
         exit(0);
     }
 
+#ifndef _WIN32
+    if (params.listen_port != "") {
+      return listen_tcp(ctx, params);
+    }
+#endif
+
     return run(ctx, params, std::cin, stdout, stderr);
 }