diff --git a/llama.cpp b/llama.cpp
index add75818b..a7ce50dd3 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -10287,9 +10287,9 @@ struct llm_build_context {
                 );
                 cb(Kcur, "Kcur", il);
 
-                cur = llm_build_kv(ctx0, model, hparams, kv_self, gf,
+                cur = llm_build_kv(ctx0, model, hparams, cparams, kv_self, gf,
                         model.layers[il].wo, nullptr,
-                        Kcur, Vcur, Qcur, KQ_mask, nullptr, n_ctx, n_tokens, kv_head, n_kv, 1.0f/sqrtf(float(n_embd_head)), cb, il);
+                        Kcur, Vcur, Qcur, KQ_mask, nullptr, n_tokens, kv_head, n_kv, 1.0f/sqrtf(float(n_embd_head)), cb, il);
             }
 
             if (il == n_layer - 1) {