torch.cuda.is_available() is redundant as apex handles that internally (#9350)

src/transformers/models/bart/modeling_bart.py

@@ -110,7 +110,6 @@ def _expand_mask(mask: torch.Tensor, dtype: torch.dtype, tgt_len: Optional[int]
 
 
 def BartLayerNorm(normalized_shape: torch.Size, eps: float = 1e-5, elementwise_affine: bool = True):
-    if torch.cuda.is_available():
     try:
         from apex.normalization import FusedLayerNorm
 

src/transformers/models/fsmt/modeling_fsmt.py

@@ -265,14 +265,12 @@ FSMT_INPUTS_DOCSTRING = r"""
 
 
 have_fused_layer_norm = False
-if torch.cuda.is_available():
-    try:
+try:
     from apex.normalization import FusedLayerNorm
 
     have_fused_layer_norm = True
-    except ImportError:
+except ImportError:
     pass
-
 LayerNorm = FusedLayerNorm if have_fused_layer_norm else torch.nn.LayerNorm
 
 

src/transformers/models/prophetnet/modeling_prophetnet.py

@@ -511,7 +511,6 @@ class ProphetNetDecoderLMOutput(ModelOutput):
 
 
 def ProphetNetLayerNorm(normalized_shape, eps=1e-5, elementwise_affine=True):
-    if torch.cuda.is_available():
     try:
         from apex.normalization import FusedLayerNorm