Update README.md

README.md

@@ -108,6 +108,14 @@ output_text = tokenizer.decode(outputs[0])
 
 We recommend using the following set of parameters for inference. Note that our model does not have the default system_prompt.
 
+### Use with vLLM
+```SHELL
+pip install vllm --upgrade
+```
+
+```SHELL
+vllm serve zhiqing/Hunyuan-MT-Chimera-7B-INT8
+```
 ```json
 {
   "top_k": 20,