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

..

generation

…

models

Use flash-attn in gemma. (#2195)

2024-05-18 19:18:59 +02:00

pipelines

…

lib.rs

…

object_detection.rs

…

quantized_nn.rs

…

quantized_var_builder.rs

Add a quantized version of recurrent-gemma. (#2054)

2024-04-13 20:07:01 +02:00

utils.rs

…