llama.cpp
6aefd112 - llama : adapt new models to F16 KQ_mask

Login via GitHub
Home
Pricing
FAQ
Install

Login via GitHub

Commit

2 years ago

llama : adapt new models to F16 KQ_mask

References

#5021 - ggml : add Flash Attention

Author

ggerganov

ggerganov

Parents

FAQ Terms Privacy Refunds Impressum

Loading