Update README.md

README.md

@@ -179,6 +179,14 @@ CLIP-like models have established themselves as the backbone for general-purpose
 
 An updated version of our [technical report](https://arxiv.org/abs/2405.20204) with details on `jina-clip-v2` is coming soon. Stay tuned!
 
+## Faster Inference: FA2, XFormers and bf16
+
+On a CUDA enabled torch environment, the model comes in `torch.bfloat16` 
+precision by default. It is highly 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.
+
 
 ## Usage
 
@@ -389,13 +397,6 @@ _, _, 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