transformers
7f552e28
- Gemma2 and flash-attention (#32188)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
Gemma2 and flash-attention (#32188) * enable flash-attn & static cache * this works, not the prev * fix for sliding window layers * not needed anymore
References
#32188 - Gemma2 and flash-attention
Author
zucchini-nlp
Parents
a3264332
Loading