From 921772104ba2219bfdc2b2980d05ebc0aa0c92a4 Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Tue, 5 Sep 2023 08:46:17 +0300
Subject: 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
---
 common/common.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'common/common.cpp')

diff --git a/common/common.cpp b/common/common.cpp
index 74e1b6fd..d4f9dbf5 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -772,7 +772,7 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
     {
         LOG("warming up the model with an empty run\n");
 
-        const std::vector<llama_token> tmp = { llama_token_bos(lctx), };
+        const std::vector<llama_token> tmp = { llama_token_bos(lctx), llama_token_eos(lctx), };
         llama_eval(lctx, tmp.data(), tmp.size(), 0, params.n_threads);
         llama_reset_timings(lctx);
     }
-- 
cgit v1.2.3