docs fix

Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>
NVIDIA · Sep 26, 2024 · f72c79f · f72c79f
1 parent 535000f
commit f72c79f
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/transformer_engine/pytorch/attention.py b/transformer_engine/pytorch/attention.py
@@ -7853,7 +7853,7 @@ class MultiheadAttention(torch.nn.Module):
     bias : bool, default = `True`
           if set to `False`, the transformer layer will not learn any additive biases.
     device : Union[torch.device, str], default = "cuda"
-          The device on which the parameters of the model will allocated. It is the user's
+          The device on which the parameters of the model will be allocated. It is the user's
           responsibility to ensure all parameters are moved to the GPU before running the
           forward pass.
     qkv_format: str, default = `sbhd`

diff --git a/transformer_engine/pytorch/transformer.py b/transformer_engine/pytorch/transformer.py
@@ -173,7 +173,7 @@ class TransformerLayer(torch.nn.Module):
           Type of activation used in MLP block.
           Options are: 'gelu', 'relu', 'reglu', 'geglu', 'swiglu', 'qgelu' and 'srelu'.
     device : Union[torch.device, str], default = "cuda"
-          The device on which the parameters of the model will allocated. It is the user's
+          The device on which the parameters of the model will be allocated. It is the user's
           responsibility to ensure all parameters are moved to the GPU before running the
           forward pass.
     attn_input_format: {'sbhd', 'bshd'}, default = 'sbhd'