Lib.rs

› Science › Machine learning
#machine-learning #tensor #blas

candle-flash-attn

Flash attention layer for the candle ML framework

by Laurent Mazare, Nicolas Patry and 97 contributors

18 releases (6 breaking)

0.7.2 Sep 29, 2024
0.6.0 Jun 29, 2024
0.4.1 Feb 28, 2024
0.3.2 Dec 20, 2023
0.3.1 Nov 12, 2023

#723 in Machine learning

Download history 49/week @ 2024-07-08 131/week @ 2024-07-15 12/week @ 2024-07-22 11/week @ 2024-07-29 10/week @ 2024-08-05 43/week @ 2024-08-12 45/week @ 2024-08-19 58/week @ 2024-08-26 43/week @ 2024-09-02 32/week @ 2024-09-09 232/week @ 2024-09-16 421/week @ 2024-09-23 122/week @ 2024-09-30 22/week @ 2024-10-07 67/week @ 2024-10-14 15/week @ 2024-10-21

367 downloads per month
Used in 9 crates (5 directly)

MIT/Apache

2.5MB
26K SLoC

candle-flash-attn

Dependencies

~33MB
~746K SLoC