Refactor how we augment llama.cpp

This changes the model for llama.cpp inclusion so we're not applying a patch,
but instead have the C++ code directly in the ollama tree, which should make it
easier to refine and update over time.

llm/dynamic_shim.h

@@ -1,6 +1,6 @@
 #include <stdlib.h>
 
-#include "server.h"
+#include "ext_server.h"
 
 #ifdef __cplusplus
 extern "C" {