diff --git a/src/llama.cpp b/src/llama.cpp
index 39e20440eea83..0a0f9efd64721 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -9258,7 +9258,7 @@ static struct ggml_tensor * llm_build_copy_mask_state(
     // FIXME: zero-out NANs?
     states = ggml_mul(ctx, states, state_mask);
 
-    // copy states which won't be changed further (between n_seqs and n_rs)
+    // copy states which won't be changed further (between n_seqs and n_kv)
     ggml_build_forward_expand(graph,
         ggml_cpy(ctx,
             ggml_view_1d(ctx, states, n_state*(n_kv - n_seqs), n_seqs*n_state*ggml_element_size(states)),