docs: update README on xformers and flash-attn

README.md

@@ -389,6 +389,14 @@ _, _, text_embeddings, image_embeddings = output
 
 </details>
 
+### On CUDA devices
+
+On a CUDA enabled torch environment, the model comes in `torch.bfloat16` 
+precision by default. When running on CUDA, it is recommended to install 
+[FlashAttention](https://github.com/Dao-AILab/flash-attention?tab=readme-ov-file#installation-and-features) 
+and [xFormers](https://github.com/facebookresearch/xformers?tab=readme-ov-file#installing-xformers) 
+to make use of their efficient attention mechanism implementations.
+
 
 ## License