[Doc] Update ROCm getting started instruction (#678)

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

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"