Refactor Dockerfile.ci to use precompiled VLLM installation and remove unused parse.py file. Update serving_chat.py to streamline rendering logic and enhance compatibility with new API. Modify OmniInputPreprocessor to directly handle SingletonDictPrompt, improving input processing efficiency.

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

docker/Dockerfile.ci

@@ -34,7 +34,7 @@ RUN uv pip install --system --upgrade --force-reinstall --prerelease=allow vllm
 RUN uv pip uninstall --system nvidia-cublas-cu12
 # Install vllm-omni into the same uv-managed Python environment used by the base image.
 # Use bash -c so that $(python3 -c ...) is expanded inside the container.
-RUN /bin/bash -c 'uv pip install --python "$(python3 -c "import sys; print(sys.executable)")" --no-cache-dir -e ".[dev]"'
+RUN /bin/bash -c 'VLLM_USE_PRECOMPILED=1 uv pip install --python "$(python3 -c "import sys; print(sys.executable)")" --no-cache-dir -e ".[dev]"'
 
 
 RUN /bin/bash -c 'FLASHINFER_CUDA_TAG="$(python3 -c "import torch; print((torch.version.cuda or \"12.4\").replace(\".\", \"\"))")" && \