diff --git a/vllm/engine/llm_engine.py b/vllm/engine/llm_engine.py
index 19e7143a..94a5b397 100644
--- a/vllm/engine/llm_engine.py
+++ b/vllm/engine/llm_engine.py
@@ -662,10 +662,10 @@ class LLMEngine:
         # decode seq_groups in scheduled_seq_groups.
         if scheduler_outputs is not None:
             num_generation_tokens_from_prefill_groups = 0.
-            if scheduler_outputs.num_prefill_groups > 0 and len(
-                    scheduler_outputs.scheduled_seq_groups
-            ) != scheduler_outputs.num_prefill_groups:
-                print("DETECTED CHUNKED")
+            # NOTE: if scheduler_outputs.num_prefill_groups > 0 and
+            # the len of scheduler_outputs.scheduled_seq_groups is !=
+            # scheduler_outputs.num_prefill_groups, this means that
+            # chunked prefills have been detected.
 
             for idx, scheduled_seq_group in enumerate(
                     scheduler_outputs.scheduled_seq_groups):