Add vLLM Usage section (vLLM-Omni day-0 support)

README.md

@@ -21,3 +21,29 @@ Most large models today are **turn-based**: they answer only when you ask. But m
 The decision of *when to act* is **learned inside the model** (from second-by-second time-aligned data + RL), not bolted on by an external turn-detector or polling loop. Vision is the first-class driver; speech (ASR/TTS) is treated as pluggable I/O.
 
 To our knowledge, this is the **first open, vision-driven interaction model** released together with its training recipe, data, and a complete deployable system.
+
+---
+## vLLM Usage
+
+[vLLM-Omni](https://github.com/vllm-project/vllm-omni) provides **day-0 support** for JoyAI-VL-Interaction! The model is a standard Qwen3-VL VLM served by a plain `vllm serve`; vLLM-Omni adds the real-time interaction layer on top — the per-second **speak / silence / delegate** orchestration, 3-tier summary memory, and pluggable ASR / TTS / delegation. For installation and full setup (browser demo, RTSP input, delegation, ASR/TTS), see the [vLLM-Omni recipe](https://github.com/vllm-project/vllm-omni/blob/main/recipes/JD/JoyAI-VL-Interaction.md).
+
+### Online Serving
+
+```bash
+# git clone https://github.com/vllm-project/vllm-omni.git
+
+# 1. Serve the model (plain `vllm serve`, NOT --omni — it is vanilla Qwen3-VL)
+vllm serve jdopensource/JoyAI-VL-Interaction-Preview \
+  --served-model-name JoyAI-VL-Interaction-Preview --port 8061 \
+  --max-model-len 131072 --enable-prefix-caching --limit-mm-per-prompt '{"image":256,"video":1}'
+
+# 2. Start the interaction orchestrator (OpenAI-compatible, :8070)
+python -m vllm_omni.experimental.fullduplex.joyvl.serving.server --port 8070 \
+  --main-backend-url http://127.0.0.1:8061/v1 --main-model JoyAI-VL-Interaction-Preview
+
+# 3. (optional) launch the self-contained Gradio demo
+pip install vllm-omni[demo]
+python vllm-omni/examples/online_serving/joyvl_interaction/app.py --server http://127.0.0.1:8070
+```
+
+Send one frame per turn (~1 fps) to `/v1/chat/completions` with an `x-session-id` header and an optional standing instruction; each reply's `interaction.action` is `silence` / `response` / `delegate`. See the recipe for the full client and capability examples.