Refactor Dockerfile.ci to streamline installation process and update vllm-omni installation method. Removed commented-out installation commands and ensured Python symlink is created.

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

docker/Dockerfile.ci

@@ -3,31 +3,13 @@ ARG VLLM_BASE_TAG=v0.17.0
 FROM ${VLLM_BASE_IMAGE}:${VLLM_BASE_TAG}
 ARG APP_DIR=/workspace/vllm-omni
 WORKDIR ${APP_DIR}
-
-COPY . .
-
-# Install system dependencies
-RUN apt-get update && \
-    apt-get install -y ffmpeg git sox libsox-fmt-all jq && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
-# Install vLLM wheel for the specific commit
-# URL format: https://wheels.vllm.ai/<commit_hash>/
-# Current vLLM wheel commit: b31e9326a7d9394aab8c767f8ebe225c65594b60 (releases/v0.17.0)
-# Note: --prerelease=allow is required because nightly/commit wheels use
-# pre-release version numbers (e.g. 2.10.0.dev...) which uv ignores by default,
-# causing it to fall back to the older stable release from PyPI.
-# RUN uv pip install --system --upgrade --force-reinstall --prerelease=allow vllm --extra-index-url https://wheels.vllm.ai/097eb544e9a22810c9b7a59e586b61627b308362
-
+# 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 uv pip install --system --no-cache-dir ".[dev]"
-# RUN uv pip install --system --upgrade \
-#     "flashinfer-cubin==0.6.4" \
-#     "nvidia-cublas-cu12==12.9.1.4" \
-#     "numpy==2.2.6"
-# RUN uv pip install --system --upgrade \
-#     "flashinfer-jit-cache==0.6.4" \
-#     --index-url https://flashinfer.ai/whl/cu129
-# RUN ln -sf /usr/bin/python3 /usr/bin/python
+
+RUN ln -sf /usr/bin/python3 /usr/bin/python
 
 ENTRYPOINT []