diff --git a/src/llama.cpp b/src/llama.cpp
index 587b53230..1303eda41 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -13854,7 +13854,7 @@ struct llm_build_context {
             // self-attention
             {
                 // compute Q and K and RoPE them
-                struct ggml_tensor * Qcur = ggml_mul_mat(ctx0, model.layers[il].wq, cur);
+                struct ggml_tensor * Qcur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wq, cur);
                 cb(Qcur, "Qcur", il);
                 if (model.layers[il].bq) {
                     Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq);