speculative : add grammar support (#2991)

* speculative : add grammar support

* grammars : add json_arr.gbnf

* grammar : add comments to new grammar file

* grammar : remove one nested level

* common : warm-up with 2 tokens - seems to work better

* speculative : print draft token pieces

* speculative : reuse grammar parser + better logs and comments

* speculative : avoid grammar_mem

* make : fix speculative build

1 files changed, 2 insertions, 0 deletions

diff --git a/llama.h b/llama.h
index 422f2852..5b95aaa8 100644
--- a/llama.h
+++ b/llama.h
@@ -410,6 +410,8 @@ extern "C" {
 
     LLAMA_API void llama_grammar_free(struct llama_grammar * grammar);
 
+    LLAMA_API struct llama_grammar * llama_grammar_copy(const struct llama_grammar * grammar);
+
     //
     // Sampling functions
     //