onnxruntime
9206b7cd
- Zhijxu/cast propagation softmax (#16408)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
Zhijxu/cast propagation softmax (#16408) enhance cast-propagation for "softmax can be put at fp16 when data flow is cast-to-fp32 > softmax > cast-to-fp16" this optimization can save gpu memory and have performance gain
References
#16408 - Zhijxu/cast propagation softmax
Author
zhijxu-MS
Parents
9407c327
Loading