Files
candle/candle-kernels
2023-07-22 15:06:35 +01:00
..
2023-07-22 15:06:35 +01:00
2023-07-22 15:06:35 +01:00
2023-06-27 11:57:27 +02:00
2023-07-22 15:06:35 +01:00

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.