Update docs/deploy_guidance.md

docs/deploy_guidance.md

@@ -8,17 +8,29 @@
 ## vLLM Deployment
 
 Here is the example to serve this model on a H200 single node with TP8 via vLLM:
+
+1. pull the Docker image.
 ```bash
-vllm serve ${MODEL_PATH} --tp 8 --trust-remote-code \
-    --tool-call-parser qwen3_coder --enable-auto-tool-choice \
-    --speculative-config $'{"method": "mtp", "num_speculative_tokens": 3}'
+docker pull jdopensource/joyai-llm-vllm:v0.13.0-joyai_llm_flash
 ```
+2. launch JoyAI-LLM Flash model with dense MTP.
+```bash
+vllm serve ${MODEL_PATH} --tp 8 --trust-remote-code \
+  --tool-call-parser qwen3_coder --enable-auto-tool-choice \
+  --speculative-config $'{"method": "mtp", "num_speculative_tokens": 3}'
 **Key notes**
 - `--tool-call-parser qwen3_coder`: Required for enabling tool calling
 
 ## SGLang Deployment
 
 Similarly, here is the example to run with TP8 on H200 in a single node via SGLang:
+
+1. pull the Docker image.
+```bash
+docker pull jdopensource/joyai-llm-sglang:v0.5.8-joyai_llm_flash
+```
+2. launch JoyAI-LLM Flash model with dense MTP.
+
 ```bash
 python3 -m sglang.launch_server --model-path ${MODEL_PATH} --tp-size 8 --trust-remote-code \
   --tool-call-parser qwen3_coder \