Update README.md

README.md

@@ -28,7 +28,7 @@ library_name: transformers
 
 # News 📢
 
-- 🔜 _(Coming Soon!) GGUF format model files will be available soon for easier local deployment._
+- 🔧`2025/10/29`: Added support for function calling on vLLM with Mi:dm 2.0 parser.
 - 📕`2025/08/08`: Published a technical blog article about Mi:dm 2.0 Model.
 - ⚡️`2025/07/04`: Released Mi:dm 2.0 Model collection on Hugging Face🤗.
 <br>
@@ -527,11 +527,32 @@ We provide a detailed description about running Mi:dm 2.0 on your local machine
 
 ## Deployment
 
+#### Basic Serving
+
 To serve Mi:dm 2.0 using [vLLM](https://github.com/vllm-project/vllm)(`>=0.8.0`) with an OpenAI-compatible API:
 ```bash
 vllm serve K-intelligence/Midm-2.0-Mini-Instruct
 ```
 
+#### With Function Calling
+
+For advanced function calling tasks, you can serve Mi:dm 2.0 with our own tool parser:
+1. Download and place [Mi:dm 2.0 parser file](https://github.com/K-intelligence-Midm/Midm-2.0/blob/main/tutorial/03_open-webui/modelfile/midm_parser.py) in your working directory.
+2. Run the following Docker command to launch the vLLM server with our custom parser file:
+    ```bash
+    docker run --rm -it --gpus all -p 8000:8000 \
+        -e HUGGING_FACE_HUB_TOKEN="<YOUR_HUGGINGFACE_TOKEN>" \
+        -v "$(pwd)/midm_parser.py:/custom/midm_parser.py" \
+        vllm/vllm-openai:v0.11.0 \
+        --model K-intelligence/Midm-2.0-Base-Instruct \
+        --enable-auto-tool-choice \
+        --tool-parser-plugin /custom/midm_parser.py \
+        --tool-call-parser midm-parser \
+        --host 0.0.0.0
+    ```
+
+>[!Note]
+> This setup is compatible with `vllm/vllm-openai:v0.8.0` and later, but we strongly recommend using `v0.11.0` for optimal stability and compatibility with our parser.
 
 ## Tutorials
 To help our end-users easily use Mi:dm 2.0, we have provided comprehensive tutorials on [github](https://github.com/K-intelligence-Midm/Midm-2.0).