Commit bd4df28
[refactor] remove conv_cache from CogVideoX VAE (huggingface#9524)
* remove conv cache from the layer and pass as arg instead
* make style
* yiyi's cleaner implementation
Co-Authored-By: YiYi Xu <[email protected]>
* sayak's compiled implementation
Co-Authored-By: Sayak Paul <[email protected]>
---------
Co-authored-by: Sayak Paul <[email protected]>
Co-authored-by: YiYi Xu <[email protected]>1 parent 1154243 commit bd4df28
File tree
1 file changed
+181
-84
lines changed- src/diffusers/models/autoencoders
1 file changed
+181
-84
lines changed
0 commit comments