add vllm image

README.md

@@ -180,15 +180,22 @@ print(decoded)
 
 For deployment, you can use vllm to create an OpenAI-compatible API endpoint.
 
-1. Install vLLM nightly:
+1. Install vLLM nightly (choose one):
+   - **Python / pip**
 
-   ```bash
-   pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
-   ```
+     ```bash
+     pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
+     ```
+
+     Python ≥3.10 is required. Please ensure vLLM version >= 0.14.0rc2.dev143+gc0a350ca7.
+
+   - **Docker (nightly image)**
 
-   **Requirements:** Python ≥3.10 is required. Please ensure vLLM version >= 0.14.0rc2.dev143+gc0a350ca7.
+     ```bash
+     docker pull vllm/vllm-openai:nightly-963dc0b865a3b6011fde7e0d938f86245dccbfac
+     ```
 
-   > **Note:** The official vLLM nightly Docker image is pending release. For now, please install from the nightly wheel index as shown above.
+     The tag above pins the nightly build we validated; update to the latest nightly tag if needed.
 
 2. Launch the server: