onnxruntime
6e895fe7
- Parallelize Max (#16745)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
Parallelize Max (#16745) It gives up to 7.5% improvement in LLaMA 7B case.
References
#16745 - Parallelize Max
Author
yihonglyu
Parents
24566058
Loading