From 27b804cea70bc8b812b35eec5caaf0e14c550781 Mon Sep 17 00:00:00 2001
From: TJian <tunjian.tan@embeddedllm.com>
Date: Wed, 7 Jan 2026 17:06:48 +0800
Subject: [PATCH] [Doc] Update ROCm getting started instruction (#678)

Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
---
 docs/getting_started/installation/gpu.md      | 15 +++++---
 .../installation/gpu/rocm.inc.md              | 38 +++++++++++++++++++
 2 files changed, 47 insertions(+), 6 deletions(-)

diff --git a/docs/getting_started/installation/gpu.md b/docs/getting_started/installation/gpu.md
index 0f6e4dd84..73c974280 100644
--- a/docs/getting_started/installation/gpu.md
+++ b/docs/getting_started/installation/gpu.md
@@ -49,15 +49,18 @@ vLLM-Omni is a Python library that supports the following GPU variants. The libr
 
 ## Set up using Docker
 
+### Pre-built images
+
+=== "NVIDIA CUDA"
+
+    --8<-- "docs/getting_started/installation/gpu/cuda.inc.md:pre-built-images"
+
+=== "AMD ROCm"
+
+    --8<-- "docs/getting_started/installation/gpu/rocm.inc.md:pre-built-images"
 
 ### Build your own docker image
 
 === "AMD ROCm"
 
     --8<-- "docs/getting_started/installation/gpu/rocm.inc.md:build-docker"
-
-### Pre-built images
-
-=== "NVIDIA CUDA"
-
-    --8<-- "docs/getting_started/installation/gpu/cuda.inc.md:pre-built-images"
diff --git a/docs/getting_started/installation/gpu/rocm.inc.md b/docs/getting_started/installation/gpu/rocm.inc.md
index 8d9eef4ea..1fa751e25 100644
--- a/docs/getting_started/installation/gpu/rocm.inc.md
+++ b/docs/getting_started/installation/gpu/rocm.inc.md
@@ -52,4 +52,42 @@ bash
 
 # --8<-- [start:pre-built-images]
 
+vLLM-Omni offers an official docker image for deployment. These images are built on top of vLLM docker images and available on Docker Hub as [vllm/vllm-omni-rocm](https://hub.docker.com/r/vllm/vllm-omni-rocm/tags). The version of vLLM-Omni indicates which release of vLLM it is based on.
+
+#### Launch vLLM-Omni Server
+Here's an example deployment command that has been verified on 2 x MI300's:
+```bash
+docker run -it \
+  --network=host \
+  --group-add=video \
+  --ipc=host \
+  --cap-add=SYS_PTRACE \
+  --security-opt seccomp=unconfined \
+  --device /dev/kfd \
+  --device /dev/dri \
+  -v <path/to/model>:/app/model \
+  -v ~/.cache/huggingface:/root/.cache/huggingface \
+  --env "HF_TOKEN=$HF_TOKEN" \
+  vllm/vllm-omni-rocm:v0.12.0rc1 \
+  vllm serve --model Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091
+```
+
+#### Launch an interactive terminal with prebuilt docker image.
+If you want to run in dev environment you can launch the docker image as follows:
+```bash
+docker run -it \
+  --network=host \
+  --group-add=video \
+  --ipc=host \
+  --cap-add=SYS_PTRACE \
+  --security-opt seccomp=unconfined \
+  --device /dev/kfd \
+  --device /dev/dri \
+  -v <path/to/model>:/app/model \
+  -v ~/.cache/huggingface:/root/.cache/huggingface \
+  --env "HF_TOKEN=$HF_TOKEN" \
+  vllm/vllm-omni-rocm:v0.12.0rc1 \
+  bash
+```
+
 # --8<-- [end:pre-built-images]