llama.cpp
6be02b59 - cuda : fix build

Login via GitHub
Home
Pricing
FAQ
Install

Login via GitHub

Commit

1 year ago

cuda : fix build

References

gg/flash-attn-wip

#5021 - ggml : add Flash Attention

Author

ggerganov

ggerganov

Parents

FAQ Terms Privacy Refunds Impressum

Loading