onnxruntime
34deae75
- changes to fusion_attention.py updated
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
5 years ago
changes to fusion_attention.py updated
References
#8106 - Fuse attention node even in case of different Q,K hidden dimensions
Author
viboga
Parents
5221a743
Loading