[ROCm] [CI] Optimize Dockerfilerocm and reduce build time on CI (#885)

Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>

docs/getting_started/installation/gpu/rocm.inc.md

@@ -34,8 +34,28 @@ DOCKER_BUILDKIT=1 docker build \
 
 #### Launch the docker image
 
+##### Launch with OpenAI API Server
+
 ```
-docker run -it \
+docker run --rm \
+--group-add=video \
+--ipc=host \
+--cap-add=SYS_PTRACE \
+--security-opt seccomp=unconfined \
+--device /dev/kfd \
+--device /dev/dri \
+-v ~/.cache/huggingface:/root/.cache/huggingface \
+--env "HF_TOKEN=$HF_TOKEN" \
+-p 8091:8091 \
+--ipc=host \
+vllm-omni-rocm \
+--model Qwen/Qwen3-Omni-30B-A3B-Instruct --port 8091
+```
+
+##### Launch with interactive session for development
+
+```
+docker run --rm -it \
 --network=host \
 --group-add=video \
 --ipc=host \
@@ -44,8 +64,9 @@ docker run -it \
 --device /dev/kfd \
 --device /dev/dri \
 -v <path/to/model>:/app/model \
-vllm-omni-rocm \
-bash
+-v ~/.cache/huggingface:/root/.cache/huggingface \
+--entrypoint bash \
+vllm-omni-rocm
 ```
 
 # --8<-- [end:build-docker]
@@ -57,8 +78,7 @@ vLLM-Omni offers an official docker image for deployment. These images are built
 #### 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 \
+docker run --rm \
   --group-add=video \
   --ipc=host \
   --cap-add=SYS_PTRACE \
@@ -68,14 +88,15 @@ docker run -it \
   -v <path/to/model>:/app/model \
   -v ~/.cache/huggingface:/root/.cache/huggingface \
   --env "HF_TOKEN=$HF_TOKEN" \
+  -p 8091:8091 \
   vllm/vllm-omni-rocm:v0.14.0 \
-  vllm serve --model Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091
+  --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 \
+docker run --rm -it \
   --network=host \
   --group-add=video \
   --ipc=host \
@@ -86,8 +107,8 @@ docker run -it \
   -v <path/to/model>:/app/model \
   -v ~/.cache/huggingface:/root/.cache/huggingface \
   --env "HF_TOKEN=$HF_TOKEN" \
-  vllm/vllm-omni-rocm:v0.14.0 \
-  bash
+  --entrypoint bash \
+  vllm/vllm-omni-rocm:v0.14.0
 ```
 
 # --8<-- [end:pre-built-images]