From efac2d469fa257c9320ac8af77b34e3cc389cc20 Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Thu, 7 Sep 2023 15:32:19 +0300
Subject: [PATCH] common : don't do warm-up with more than n_batch tokens
 (close #3058)

ggml-ci
---
 common/common.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/common/common.cpp b/common/common.cpp
index 22f65ac46..28b7c6300 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -773,7 +773,7 @@ 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), llama_token_eos(lctx), };
-        llama_eval(lctx, tmp.data(), tmp.size(), 0, params.n_threads);
+        llama_eval(lctx, tmp.data(), std::min(tmp.size(), (size_t) params.n_batch), 0, params.n_threads);
         llama_reset_timings(lctx);
     }