mirror of
https://github.com/huggingface/candle.git
synced 2025-06-16 02:38:10 +00:00
candle-kernels
This crate contains CUDA kernels used from candle. Some of these implementations come from the dfdx crate.
The ln*
files come from the flash-attention
repo and have been edited so as
to compile without including the PyTorch codebase.