Update README.md

README.md

@@ -22,7 +22,7 @@ print(responds)
 ```
 
 # Note
-1. You can alse inference with [vLLM](https://github.com/vllm-project/vllm), which will be compatible with this repo and has a much higher inference throughput.
+1. You can alse inference with [vLLM](https://github.com/vllm-project/vllm)(>=0.4.1), which is compatible with this repo and has a much higher inference throughput.
 2. The precision of model weights in this repo is bfloat16. Manual convertion is needed for other kinds of dtype.
 3. For more details, please refer to our [github repo](https://github.com/OpenBMB/MiniCPM).