fix: remove deprecated is_torch_fx_available for transformers v5 compat

modeling_llada2_moe.py

@@ -52,7 +52,6 @@ from transformers.utils import (
     logging,
     replace_return_docstrings,
 )
-from transformers.utils.import_utils import is_torch_fx_available
 from .configuration_llada2_moe import LLaDA2MoeConfig
 from transformers.generation.utils import GenerationMixin
 
@@ -62,13 +61,6 @@ if is_flash_attn_2_available():
     from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input  # noqa
 
 
-# This makes `_prepare_4d_causal_attention_mask` a leaf function in the FX graph.
-# It means that the function will not be traced through and simply appear as a node in the graph.
-if is_torch_fx_available():
-    if not is_torch_greater_or_equal_than_1_13:
-        import torch.fx
-
-    _prepare_4d_causal_attention_mask = torch.fx.wrap(_prepare_4d_causal_attention_mask)
 
 
 logger = logging.get_logger(__name__)