install sglang in virtual env instead of system path (#30612)

docker/Dockerfile

@@ -43,15 +43,14 @@ RUN --mount=type=cache,target=/var/cache/apt,id=base-apt \
     && apt install -y --no-install-recommends python3.12-full python3.12-dev \
     && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.12 2 \
     && update-alternatives --set python3 /usr/bin/python3.12 \
-    && wget -q https://bootstrap.pypa.io/get-pip.py \
-    && python3 get-pip.py --break-system-packages \
-    && rm get-pip.py \
-    # Allow pip to install packages globally (PEP 668 workaround for Ubuntu 24.04)
-    && python3 -m pip config set global.break-system-packages true \
     # Fix for apt-add-repository
     && cd /usr/lib/python3/dist-packages/ \
     && ln -s apt_pkg.cpython-312-*-linux-gnu.so apt_pkg.so
 
+# create virtual env for sglang to avoid conflict with system python packages
+RUN python3 -m venv /opt/sglang
+ENV PATH="/opt/sglang/bin:${PATH}"
+
 # Install system dependencies (organized by category for better caching)
 RUN --mount=type=cache,target=/var/cache/apt,id=base-apt \
     apt-get update && apt-get install -y --no-install-recommends \
@@ -313,12 +312,12 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     && mkdir -p /flashinfer_jit_output \
     # flashinfer-cubin is CUDA-version-agnostic, unlike jit-cache, so its index-url has no cu${CUINDEX} suffix
     && python3 -m pip install flashinfer-cubin==${FLASHINFER_VERSION} --index-url https://flashinfer.ai/whl \
-    && cp -r /usr/local/lib/python3.12/dist-packages/flashinfer_cubin /flashinfer_jit_output/ \
-    && cp -r /usr/local/lib/python3.12/dist-packages/flashinfer_cubin-*.dist-info /flashinfer_jit_output/ \
+    && cp -r /opt/sglang/lib/python3.12/site-packages/flashinfer_cubin /flashinfer_jit_output/ \
+    && cp -r /opt/sglang/lib/python3.12/site-packages/flashinfer_cubin-*.dist-info /flashinfer_jit_output/ \
     && if [ "$INSTALL_FLASHINFER_JIT_CACHE" = "1" ]; then \
         python3 -m pip install flashinfer-jit-cache==${FLASHINFER_VERSION} --index-url https://flashinfer.ai/whl/cu${CUINDEX} \
-        && cp -r /usr/local/lib/python3.12/dist-packages/flashinfer_jit_cache /flashinfer_jit_output/ \
-        && cp -r /usr/local/lib/python3.12/dist-packages/flashinfer_jit_cache-*.dist-info /flashinfer_jit_output/ ; \
+        && cp -r /opt/sglang/lib/python3.12/site-packages/flashinfer_jit_cache /flashinfer_jit_output/ \
+        && cp -r /opt/sglang/lib/python3.12/site-packages/flashinfer_jit_cache-*.dist-info /flashinfer_jit_output/ ; \
     fi
 
 ########################################################
@@ -432,7 +431,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     fi && rm -rf /tmp/wheels/hpc-ops
 
 # Copy flashinfer cubin (always) and jit-cache (if installed) packages
-COPY --from=flashinfer_cache /flashinfer_jit_output/ /usr/local/lib/python3.12/dist-packages/
+COPY --from=flashinfer_cache /flashinfer_jit_output/ /opt/sglang/lib/python3.12/site-packages/
 
 # Copy dev tools
 COPY --from=devtools_builder /tools/diff-so-fancy /usr/local/bin/
@@ -644,11 +643,11 @@ RUN --mount=type=cache,target=/root/.cache/pip \
          [ "$success" = "1" ] ) \
     && mkdir -p /root/.cache/huggingface /root/.cache/sglang \
     && ( if [ -f python/kernels.lock ]; then mv python/kernels.lock /root/.cache/sglang/; fi ) \
-    && ( find /usr/local/lib/python3.12/dist-packages -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null || true )
+    && ( find /opt/sglang/lib/python3.12/site-packages -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null || true )
 
 
 # Install pre-built gateway artifacts from parallel builder
-COPY --from=gateway_builder /build/sgl-model-gateway-bin /usr/local/bin/sgl-model-gateway
+COPY --from=gateway_builder /build/sgl-model-gateway-bin /opt/sglang/bin/sgl-model-gateway
 COPY --from=gateway_builder /build/gateway_wheels /tmp/gateway_wheels
 RUN --mount=type=cache,target=/root/.cache/pip \
     python3 -m pip install --force-reinstall /tmp/gateway_wheels/*.whl \
@@ -753,14 +752,13 @@ RUN --mount=type=cache,target=/var/cache/apt,id=runtime-apt \
     && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.12 2 \
     && update-alternatives --set python3 /usr/bin/python3.12 \
     && ln -sf /usr/bin/python3.12 /usr/bin/python \
-    && wget -q https://bootstrap.pypa.io/get-pip.py \
-    && python3 get-pip.py --break-system-packages \
-    && rm get-pip.py \
-    # Allow pip to install packages globally (PEP 668 workaround for Ubuntu 24.04)
-    && python3 -m pip config set global.break-system-packages true \
     && rm -rf /var/lib/apt/lists/* \
     && apt-get clean
 
+# create virtual env for sglang to avoid conflict with system python packages
+RUN python3 -m venv /opt/sglang
+ENV PATH="/opt/sglang/bin:${PATH}"
+
 # Set up locale
 RUN apt-get update && apt-get install -y --no-install-recommends locales \
     && locale-gen en_US.UTF-8 \
@@ -782,19 +780,19 @@ RUN --mount=type=cache,target=/var/cache/apt,id=runtime-apt \
     && rm -rf /var/lib/apt/lists/*
 
 # Copy Python site-packages from framework (already cleaned of __pycache__/tests/pyc files)
-COPY --from=framework_final /usr/local/lib/python3.12/dist-packages /usr/local/lib/python3.12/dist-packages
+COPY --from=framework_final /opt/sglang/lib/python3.12/site-packages /opt/sglang/lib/python3.12/site-packages
 
 # Copy SGLang workspace
 COPY --from=framework_final /sgl-workspace /sgl-workspace
 
 # Copy sgl-model-gateway binary
-COPY --from=framework_final /usr/local/bin/sgl-model-gateway /usr/local/bin/sgl-model-gateway
+COPY --from=framework_final /opt/sglang/bin/sgl-model-gateway /opt/sglang/bin/sgl-model-gateway
 
 # Copy sglang binary
-COPY --from=framework_final /usr/local/bin/sglang /usr/local/bin/sglang
+COPY --from=framework_final /opt/sglang/bin/sglang /opt/sglang/bin/sglang
 
 # Copy py-spy binary
-COPY --from=framework_final /usr/local/bin/py-spy /usr/local/bin/py-spy
+COPY --from=framework_final /opt/sglang/bin/py-spy /opt/sglang/bin/py-spy
 
 # Copy cache for kernels from kernels community
 COPY --from=framework_final /root/.cache/huggingface /root/.cache/huggingface