search

lucidrains / audiolm-pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
MIT License
2.32k stars 249 forks source link

fix wrong tensor assignment of the output of attention #265

Closed biendltb closed 5 months ago

biendltb commented 5 months ago

The output of the Attention should be assigned back to x. The attn_out is not used anywhere. So this is a bug in the code.

lucidrains commented 5 months ago

@biendltb oh yes, was introduced when adding the kv cache. thanks for catching this!