diff --git a/lightllm/server/router/model_infer/mode_backend/chunked_prefill/impl.py b/lightllm/server/router/model_infer/mode_backend/chunked_prefill/impl.py
index f2b0fab49..35e68136d 100644
--- a/lightllm/server/router/model_infer/mode_backend/chunked_prefill/impl.py
+++ b/lightllm/server/router/model_infer/mode_backend/chunked_prefill/impl.py
@@ -70,12 +70,18 @@ def infer_loop(self):
                 run_way = self.control_state_machine.select_run_way(prefill_reqs=prefill_reqs, decode_reqs=decode_reqs)
 
                 if run_way.is_prefill():
+                    # 进行一次流同步，保证 _try_read_new_reqs 中的一些算子操作，必然已经完成。
+                    # 防止后续的推理流程读取到显存中可能存在错误的数据。
+                    g_infer_context.get_overlap_stream().wait_stream(torch.cuda.current_stream())
                     self.prefill(
                         event_pack=event_pack,
                         prefill_reqs=prefill_reqs,
                     )
                     continue
                 elif run_way.is_decode():
+                    # 进行一次流同步，保证 _try_read_new_reqs 中的一些算子操作，必然已经完成。
+                    # 防止后续的推理流程读取到显存中可能存在错误的数据。
+                    g_infer_context.get_overlap_stream().wait_stream(torch.cuda.current_stream())
                     self.decode(
                         event_pack=event_pack,
                         decode_reqs=decode_reqs,
diff --git a/test/benchmark/static_inference/profile_demo.py b/test/benchmark/static_inference/profile_demo.py
new file mode 100644
index 000000000..cfe5d315f
--- /dev/null
+++ b/test/benchmark/static_inference/profile_demo.py
@@ -0,0 +1,15 @@
+import torch
+import numpy as np
+from torch.profiler import profile, record_function, ProfilerActivity
+
+torch.cuda.synchronize()
+with profile(
+    activities=[ProfilerActivity.CPU, ProfilerActivity.CUDA],
+    record_shapes=False,
+    profile_memory=False,
+    on_trace_ready=torch.profiler.tensorboard_trace_handler("./log/"),
+) as prof:
+    # test cuda code
+    pass
+
+print(prof.key_averages().table(sort_by="cuda_time_total", row_limit=20))