Update sharded_moe.py

Author: xenshinu

deepspeed/moe/sharded_moe.py

@@ -329,7 +329,7 @@ def top2gating(logits: Tensor,
     l_aux = torch.mean(me * ce) * num_experts * num_experts
 
     # gating decisions
-    exp_counts = torch.sum(mask1 + mask2, dim=0).detach().to(logits.device) 
+    exp_counts = torch.sum(mask1 + mask2, dim=0).detach().to(logits.device)
 
     if drop_tokens:
         # Calculate configured capacity and remove locations outside capacity from mask