onnxruntime
e7e0c20e
- [QNN EP] Fuse scale into softmax (#24809)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
269 days ago
[QNN EP] Fuse scale into softmax (#24809) QNN [Softmax op defines pre-scale (`beta`)](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/MasterOpDef.html#softmax) that we can fold constant scalar multiply into it.
Author
qti-yuduo
Committer
adrianlizarraga
Parents
52af0b45
Loading