ggml
ad9d6e65
- CUDA: fix typo in FlashAttention code (llama/13926)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
364 days ago
CUDA: fix typo in FlashAttention code (llama/13926)
References
#1258 - sync : llama.cpp
Author
JohannesGaessler
Committer
ggerganov
Parents
c6689ee5
Loading
