Update README.md

README.md

@@ -16,8 +16,22 @@ tags:
   **59G -> 32G memory decrease**
 
   **speedup 30%**
+  
+  **Start the vLLM server**
+  
+  vllm serve Hyper-AI/gemma-4-31B-it-fp8 --max-model-len 32768
+
+  **To enable thinking/reasoning and tool calling:**
+
+  vllm serve Hyper-AI/gemma-4-31B-it-fp8 \
+    --max-model-len 32768 \
+    --reasoning-parser gemma4 \
+    --tool-call-parser gemma4 \
+    --enable-auto-tool-choice
+
+
+
 
-  **vllm serve can run**
 
 <div align="center">
   <img src=https://ai.google.dev/gemma/images/gemma4_banner.png>