diff --git a/fastdeploy/entrypoints/openai/serving_completion.py b/fastdeploy/entrypoints/openai/serving_completion.py
index fd86fe273cb..56a8980882b 100644
--- a/fastdeploy/entrypoints/openai/serving_completion.py
+++ b/fastdeploy/entrypoints/openai/serving_completion.py
@@ -545,7 +545,9 @@ async def completion_stream_generator(
                         reasoning_content="",
                         arrival_time=arrival_time,
                         logprobs=logprobs_res,
-                        prompt_logprobs=clamp_prompt_logprobs(prompt_logprobs_res),
+                        prompt_logprobs=(
+                            clamp_prompt_logprobs(prompt_logprobs_res) if not request.return_token_ids else None
+                        ),
                         draft_logprobs=draft_logprobs_res,
                         speculate_metrics=output_speculate_metrics,
                     )
diff --git a/fastdeploy/utils.py b/fastdeploy/utils.py
index 9352e6ab881..2796b931c2f 100644
--- a/fastdeploy/utils.py
+++ b/fastdeploy/utils.py
@@ -1154,7 +1154,7 @@ def _bos_download(bos_client, link):
 console_logger = get_logger("console", "console.log", print_to_console=True)
 spec_logger = get_logger("speculate", "speculate.log")
 zmq_client_logger = get_logger("zmq_client", "zmq_client.log")
-trace_logger = FastDeployLogger().get_trace_logger("trace_logger", "trace_logger.log")
+trace_logger = FastDeployLogger().get_trace_logger("trace", "trace.log")
 router_logger = get_logger("router", "router.log")
 fmq_logger = get_logger("fmq", "fmq.log")