torch_to_nnef.op.aten.attn

Attention mechanisms.

Functions:

Name	Description
scaled_dot_product_attention	Translate operator: aten::scaled_dot_product_attention to NNEF.

scaled_dot_product_attention

scaled_dot_product_attention(g, node, name_to_tensor, inference_target, **kwargs)

Translate operator: aten::scaled_dot_product_attention to NNEF.

reference

https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html