diff --git a/docs/getting_started/installation/gpu/rocm.inc.md b/docs/getting_started/installation/gpu/rocm.inc.md
index a98a3cbe9..1a8ffb612 100644
--- a/docs/getting_started/installation/gpu/rocm.inc.md
+++ b/docs/getting_started/installation/gpu/rocm.inc.md
@@ -23,15 +23,6 @@ vLLM-Omni current recommends the steps in under setup through Docker Images.
 DOCKER_BUILDKIT=1 docker build -f docker/Dockerfile.rocm -t vllm-omni-rocm .
 ```
 
-If you want to specify which GPU Arch to build for to cutdown build time:
-
-```bash
-DOCKER_BUILDKIT=1 docker build \
-  -f docker/Dockerfile.rocm \
-  --build-arg PYTORCH_ROCM_ARCH="gfx942;gfx950" \
-  -t vllm-omni-rocm .
-```
-
 #### Launch the docker image
 
 ##### Launch with OpenAI API Server
diff --git a/examples/offline_inference/qwen3_tts/README.md b/examples/offline_inference/qwen3_tts/README.md
index 266227c4b..eab66fe14 100644
--- a/examples/offline_inference/qwen3_tts/README.md
+++ b/examples/offline_inference/qwen3_tts/README.md
@@ -13,6 +13,15 @@ Qwen3 TTS provides multiple task variants for speech generation:
 ## Setup
 Please refer to the [stage configuration documentation](https://docs.vllm.ai/projects/vllm-omni/en/latest/configuration/stage_configs/) to configure memory allocation appropriately for your hardware setup.
 
+### ROCm Dependencies
+
+You will need to install these two dependencies `onnxruntime-rocm` and `sox`.
+
+```
+pip uninstall onnxruntime # should be removed before we can install onnxruntime-rocm
+pip install onnxruntime-rocm sox
+```
+
 ## Quick Start
 
 Run a single sample for a task: