Update README.md

README.md

@@ -57,12 +57,14 @@ docker run -it \
 #### 单机推理
 ```bash
 ## serve启动
-vllm serve Qwen/Qwen3.6-35B-A3B \
+vllm serve /public/home/raojy/project/model_code/qwen36 \
     --port 8001 \
     --trust-remote-code \
     --dtype bfloat16 \
     --tensor-parallel-size 4 \
-    --gpu-memory-utilization 0.925 
+    --gpu-memory-utilization 0.925 \
+    --enable-auto-tool-choice \
+    --tool-call-parser qwen3_coder
 
 ## client访问
  curl -X POST "http://localhost:8001/v1/chat/completions"   -H "Content-Type: application/json"   -d '{