Update README.md

README.md

@@ -105,7 +105,7 @@ print("result:", result)
 
 ### Using vLLM
 
-[vllm](https://github.com/vllm-project/vllm/tree/main) github library. Python-only [build](https://docs.vllm.ai/en/latest/getting_started/installation/gpu.html#set-up-using-python-only-build-without-compilation).
+VLLM>=0.10.2 (excluding 0.11.0)
 
 ```bash
 # 80G * 16 GPU