diff --git a/src/llama.cpp b/src/llama.cpp
index b2c302915d5a8..24356d2b439c8 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -3259,10 +3259,7 @@ static void llama_kv_cache_seq_add(
     if (p0 < 0) p0 = 0;
     if (p1 < 0) p1 = std::numeric_limits<llama_pos>::max();
     // If there is no range then return early to avoid looping over the cache.
-    if (p0 == p1) {
-        cache.head = 0;
-        return;
-    }
+    if (p0 == p1) return;
 
     if (cache.recurrent) {
         // for Mamba-like models, only the pos needs to be shifted