Make graph_max_nodes vary by ubatch size (#17794)

* Make graph_max_nodes vary by ubatch size for models where chunking might explode the graph

* Update src/llama-context.h

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

* Add missing const

---------

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

src/llama-context.h

@@ -197,7 +197,7 @@ private:
     //
 
 public:
-    uint32_t graph_max_nodes() const;
+    uint32_t graph_max_nodes(uint32_t n_tokens) const;
 
     // can reuse the llm_graph_result instance of the context (for example to update a memory module)
     llm_graph_result * get_gf_res_reserve() const;