onnxruntime
05d1c56b
- Support for BNSH format
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
Support for BNSH format
References
#17674 - [CUDA] GroupQueryAttention operator using FlashAttention
Author
aciddelgado
Parents
365d0b51
Loading