Files
candle/candle-transformers
Laurent Mazare 7ebc3548e1 Use flash-attn in gemma. (#2195)
* Use flash-attn in gemma.

* Fix flash-attn for head dim 256.
2024-05-18 19:18:59 +02:00
..
2024-05-18 19:18:59 +02:00
2024-03-23 15:26:09 +01:00
2024-03-02 18:50:01 +01:00

candle-transformers