From 788b4d199efc06c5c096858eec188b071b3d9b4d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Stanis=C5=82aw=20Szymczyk?= <sszymczy@gmail.com>
Date: Fri, 9 Aug 2024 21:58:13 +0200
Subject: [PATCH] common : call llama_decode() during warmup only if the model
 has decoder

---
 common/common.cpp | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/common/common.cpp b/common/common.cpp
index 560e20d08..d3d896115 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -2156,7 +2156,9 @@ struct llama_init_result llama_init_from_gpt_params(gpt_params & params) {
             tmp.clear();
             tmp.push_back(decoder_start_token_id);
         }
-        llama_decode(lctx, llama_batch_get_one(tmp.data(), std::min(tmp.size(), (size_t) params.n_batch), 0, 0));
+        if (llama_model_has_decoder(model)) {
+            llama_decode(lctx, llama_batch_get_one(tmp.data(), std::min(tmp.size(), (size_t) params.n_batch), 0, 0));
+        }
         llama_kv_cache_clear(lctx);
         llama_synchronize(lctx);
         llama_reset_timings(lctx);