onnxruntime
492c59f7
- flash attention flag in packed attention op test and a few more benchmarks for roli
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
flash attention flag in packed attention op test and a few more benchmarks for roli
References
#17227 - Flash Attention v2 MHA
Author
aciddelgado
Parents
ee2296fc
Loading