diff --git a/colossalai/shardformer/modeling/opt.py b/colossalai/shardformer/modeling/opt.py
index 8f841c8a6..81521c30b 100644
--- a/colossalai/shardformer/modeling/opt.py
+++ b/colossalai/shardformer/modeling/opt.py
@@ -58,20 +58,6 @@ class OPTPipelineForwards:
     under pipeline setting.
     """
 
-    @staticmethod
-    def _expand_mask(mask: torch.Tensor, dtype: torch.dtype, tgt_len: Optional[int] = None):
-        """
-        Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
-        """
-        bsz, src_len = mask.size()
-        tgt_len = tgt_len if tgt_len is not None else src_len
-
-        expanded_mask = mask[:, None, None, :].expand(bsz, 1, tgt_len, src_len).to(dtype)
-
-        inverted_mask = 1.0 - expanded_mask
-
-        return inverted_mask.masked_fill(inverted_mask.to(torch.bool), torch.finfo(dtype).min)
-
     @staticmethod
     def opt_model_forward(
         self: OPTModel,