Merge pull request #380 from alibaba-damo-academy/main

yhliang

2023-04-18 9817785c66a13caa681a8e9e272f2ae949233542

 funasr/export/models/modules/multihead_att.py

@@ -75,8 +75,10 @@
    return x, cache


import torch.fx
torch.fx.wrap('preprocess_for_attn')
torch_version = tuple([int(i) for i in torch.__version__.split(".")[:2]])
if torch_version >= (1, 8):
    import torch.fx
    torch.fx.wrap('preprocess_for_attn')


class MultiHeadedAttentionSANMDecoder(nn.Module):