[Doc] Fix the version in the documentation to v0.14.0rc1; fix dockerfile.rocm entrypoint (#913)

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

docker/Dockerfile.rocm

@@ -17,6 +17,10 @@ RUN mkdir -p ${COMMON_WORKDIR}/vllm-omni
 COPY . ${COMMON_WORKDIR}/vllm-omni
 RUN cd ${COMMON_WORKDIR}/vllm-omni && uv pip install --python "$(python3 -c 'import sys; print(sys.executable)')" --no-cache-dir ".[dev]"
 
+# When we are installing onnxruntime-rocm, we need to uninstall the system-installed onnxruntime first.
+# These are the dependencies of Qwen3-TTS.
+RUN uv pip uninstall onnxruntime --system && uv pip install --no-cache-dir onnxruntime-rocm sox --system
+
 RUN ln -sf /usr/bin/python3 /usr/bin/python
 
 CMD ["/bin/bash"]
@@ -25,4 +29,4 @@ ENTRYPOINT []
 
 #Set entrypoint for vllm-openai official images
 FROM final AS vllm-openai
-ENTRYPOINT ["vllm", "serve"]
+ENTRYPOINT ["vllm", "serve", "--omni"]

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

@@ -93,7 +93,7 @@ docker run --runtime nvidia --gpus 2 \
     --env "HF_TOKEN=$HF_TOKEN" \
     -p 8091:8091 \
     --ipc=host \
-    vllm/vllm-omni:v0.14.0 \
+    vllm/vllm-omni:v0.14.0rc1 \
     --model Qwen/Qwen3-Omni-30B-A3B-Instruct --port 8091
 ```
 

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

@@ -80,7 +80,7 @@ docker run --rm \
   -v ~/.cache/huggingface:/root/.cache/huggingface \
   --env "HF_TOKEN=$HF_TOKEN" \
   -p 8091:8091 \
-  vllm/vllm-omni-rocm:v0.14.0 \
+  vllm/vllm-omni-rocm:v0.14.0rc1 \
   --model Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091
 ```
 
@@ -99,7 +99,7 @@ docker run --rm -it \
   -v ~/.cache/huggingface:/root/.cache/huggingface \
   --env "HF_TOKEN=$HF_TOKEN" \
   --entrypoint bash \
-  vllm/vllm-omni-rocm:v0.14.0
+  vllm/vllm-omni-rocm:v0.14.0rc1
 ```
 
 # --8<-- [end:pre-built-images]