import DynamicLayer

modeling_bailing_moe_linear_v2.py

@@ -28,7 +28,7 @@ import torch.nn.functional as F
 from torch import nn
 
 from transformers.activations import ACT2FN
-from transformers.cache_utils import Cache, DynamicCache
+from transformers.cache_utils import Cache, DynamicCache, DynamicLayer
 from transformers.modeling_attn_mask_utils import (
     AttentionMaskConverter,
     _prepare_4d_attention_mask,