diff --git a/paddle/fluid/inference/api/details/zero_copy_tensor.cc b/paddle/fluid/inference/api/details/zero_copy_tensor.cc
index 52204ff3658f450a17233d5e93b9e1a689f699e2..147db87a101d42013a2fc69e65905686ad14afa8 100644
--- a/paddle/fluid/inference/api/details/zero_copy_tensor.cc
+++ b/paddle/fluid/inference/api/details/zero_copy_tensor.cc
@@ -463,7 +463,7 @@ void Tensor::CopyToCpuImpl(T *data,
                          t_data,
                          ele_num * sizeof(T),
                          dev_ctx->stream());
-// TODO(wangran16): sync_stream
+    dev_ctx->GetStream()->Synchronize();
 #else
     PADDLE_THROW(paddle::platform::errors::InvalidArgument(
         "The analysis predictor supports CPU, GPU, NPU and XPU now."));