[NFC] polish colossalai/nn/layer/parallel_2d/layers.py code style (#976)

colossalai/nn/layer/parallel_2d/layers.py

@@ -182,7 +182,7 @@ class Linear2D(ParallelLayer):
     def forward(self, x: Tensor) -> Tensor:
         # input: [m/q, n/q, k/q]
         # output: [m/q, n/q, h/q]
-        out_shape = x.shape[:-1] + (self.hidden_size_per_partition, )
+        out_shape = x.shape[:-1] + (self.hidden_size_per_partition,)
 
         output = Matmul_AB_2D.apply(x, self.weight, self.summa_dim, out_shape, self.row_rank, self.col_rank,
                                     ParallelMode.PARALLEL_2D_ROW, ParallelMode.PARALLEL_2D_COL, self.data_parallel_rank,
@@ -1012,7 +1012,7 @@ class Classifier2D(ParallelLayer):
             destination.update(local_state)
 
     def forward(self, input_: Tensor) -> Tensor:
-        out_shape = input_.shape[:-1] + (self.num_classes, )
+        out_shape = input_.shape[:-1] + (self.num_classes,)
 
         return classifier_2d(input_, self.weight, self.bias, self.summa_dim, out_shape, self.row_rank, self.col_rank,
                              ParallelMode.PARALLEL_2D_ROW, ParallelMode.PARALLEL_2D_COL, self.data_parallel_rank,
@@ -1186,7 +1186,7 @@ class VocabParallelClassifier2D(ParallelLayer):
     def forward(self, x: Tensor) -> Tensor:
         # input: [m/q, n/q, k/q]
         # output: [m/q, n/q, h/q]
-        out_shape = x.shape[:-1] + (self.output_size_per_partition, )
+        out_shape = x.shape[:-1] + (self.output_size_per_partition,)
 
         output = Matmul_ABT_2D.apply(x, self.weight, self.summa_dim, out_shape, self.row_rank, self.col_rank,
                                      ParallelMode.PARALLEL_2D_ROW, ParallelMode.PARALLEL_2D_COL,