diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py
index 04d2ee0396..841dcd7c4d 100644
--- a/unsloth/models/llama.py
+++ b/unsloth/models/llama.py
@@ -449,6 +449,7 @@ def LlamaAttention_fast_forward(
     else:
         # Grouped query attention
         if SDPA_HAS_GQA:
+            print("##")
             # Needs (batch_size, n_heads, seq_len, head_dim)
             # is_casual and attention_mask must not be both set!
             A = scaled_dot_product_attention(Q, K, V, attn_mask = attention_mask, is_causal = False, enable_gqa = n_groups != 1)