diff --git a/llama.cpp b/llama.cpp
index 5e05b4126..90dc1b11f 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -5643,10 +5643,6 @@ struct llm_build_context {
         struct ggml_tensor * inp_pos = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_tokens);
         cb(inp_pos, "inp_pos", -1);
 
-        // KQ_scale
-        struct ggml_tensor * KQ_scale = ggml_new_tensor_1d(ctx0, GGML_TYPE_F32, 1);
-        cb(KQ_scale, "KQ_scale", -1);
-
         // KQ_mask (mask for 1 head, it will be broadcasted to all heads)
         struct ggml_tensor * KQ_mask = ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, n_kv, n_tokens, 1);
         cb(KQ_mask, "KQ_mask", -1);