diff --git a/S1/35/prompt.txt b/S1/35/prompt.txt
index d0bcc70..07029a6 100644
--- a/S1/35/prompt.txt
+++ b/S1/35/prompt.txt
@@ -27,6 +27,7 @@ The goal is to create a single, highly-efficient CUDA kernel pass that addresses
 This strategy transforms a multi-stage, memory-bound operation into a single-pass, compute-efficient, and numerically stable kernel, yielding substantial performance improvements.
 
 You are given the following architecture:
+
 import torch
 import torch.nn as nn
 
diff --git a/S1/35/run_code.py b/S1/35/run_code.py
index aff0428..03af26f 100644
--- a/S1/35/run_code.py
+++ b/S1/35/run_code.py
@@ -21,6 +21,7 @@ def run_benchmark():
     torch_model.eval()
     cuda_model.eval()
 
+
     print("-------------------- 精度对齐验证 --------------------")
     with torch.no_grad():
         # 预热GPU
diff --git a/S1/35/softmarginloss_cuda.py b/S1/35/softmarginloss_cuda.py
index 9c3605b..c59980c 100644
--- a/S1/35/softmarginloss_cuda.py
+++ b/S1/35/softmarginloss_cuda.py
@@ -85,7 +85,6 @@ __global__ void soft_margin_loss_reduce_kernel_stage1(
     }
 }
 
-
 torch::Tensor soft_margin_loss_cuda_forward(
     const torch::Tensor& input, 
     const torch::Tensor& target,
diff --git a/S1/35/softmarginloss_torch.py b/S1/35/softmarginloss_torch.py
index 160c5f9..598c263 100644
--- a/S1/35/softmarginloss_torch.py
+++ b/S1/35/softmarginloss_torch.py
@@ -18,6 +18,7 @@ class Model(nn.Module):
         return self.loss_fn(input_tensor, target_tensor)
 
 def get_inputs():
+    
     """
     生成用于测试的输入张量。
     """