update README

README.md

@@ -69,6 +69,9 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 ### vLLM (OpenAI-compatible serving):
 
+[vLLM](https://github.com/vllm-project/vllm) is a high-throughput and memory-efficient inference and serving engine for LLMs.
+`vllm>=0.9.0` is recommended.
+
 ```bash
 MODEL_PATH="OpenMedZoo/SafeMed-R1"  # or a local path
 PORT=50050