diff --git a/applications/ColossalChat/coati/distributed/grpo_consumer.py b/applications/ColossalChat/coati/distributed/grpo_consumer.py
index a2c3e03d6..424d46098 100644
--- a/applications/ColossalChat/coati/distributed/grpo_consumer.py
+++ b/applications/ColossalChat/coati/distributed/grpo_consumer.py
@@ -530,4 +530,4 @@ class GRPOConsumer(BaseConsumer):
         model = self.policy_model.unwrap()
         state_dict = model.state_dict()
         state_dict["consumer_global_step"] = torch.tensor([self.global_step], device=self.device)
-        return state_dict
\ No newline at end of file
+        return state_dict
diff --git a/colossalai/shardformer/modeling/qwen3.py b/colossalai/shardformer/modeling/qwen3.py
index 437693800..5f96f5f49 100644
--- a/colossalai/shardformer/modeling/qwen3.py
+++ b/colossalai/shardformer/modeling/qwen3.py
@@ -273,7 +273,7 @@ class Qwen3PipelineForwards:
         hidden_states: Optional[torch.FloatTensor] = None,
         stage_index: Optional[List[int]] = None,
         shard_config: ShardConfig = None,
-        **kwargs
+        **kwargs,
     ):
         r"""
         Args: