Update README.md

README.md

@@ -70,7 +70,7 @@ curl http://localhost:8000/v1/chat/completions \
 ```
 
 ## How to use advanced vllm options
-Description of each option  
+For maximum performance, we highly recommend using the options below.  
 ```--compilation_config '{"full_cuda_graph": true}'``` : Activates cuda [full graph capture](https://docs.vllm.ai/en/stable/design/cuda_graphs/#cudagraphmodes)  
 ```--rope-scaling '{"rope_type":"yarn","factor":2.0,"original_max_position_embeddings":65536}'```: Apply [yarn](https://arxiv.org/abs/2309.00071) to support 128K context length  
 ```--enable-auto-tool-choice --tool-call-parser hermes``` : Enables [tool calling](https://docs.vllm.ai/en/latest/features/tool_calling/)