[XPU][DOCKER] update dockerfile.xpu after main repo updating to pt2.11 (#3393)

Signed-off-by: Chendi Xue <chendi.xue@intel.com>

docker/Dockerfile.xpu

@@ -14,8 +14,9 @@ RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRO
 RUN apt clean && apt-get update -y && \
     apt-get install -y --no-install-recommends --fix-missing \
     curl \
-    espeak-ng \
+    ffmpeg \
     git \
+    libsndfile1 \
     libsm6 \
     libxext6 \
     libgl1 \
@@ -28,8 +29,20 @@ RUN apt clean && apt-get update -y && \
     python3.12-dev \
     python3-pip
 
-RUN apt update && apt upgrade -y && \
-    apt install -y intel-oneapi-compiler-dpcpp-cpp-2025.3
+# Add oneAPI repo, pin oneAPI to 2025.3, then install pinned packages in one layer.
+RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null && \
+    echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list && \
+    printf '%s\n' \
+    'Package: intel-oneapi-* intel-deep-learning-essentials* intel-pti*' \
+    'Pin: version 2025.3*' \
+    'Pin-Priority: 1001' \
+    > /etc/apt/preferences.d/oneapi-2025.3.pref && \
+    apt-get update -y && \
+    apt-get install -y --no-install-recommends \
+    intel-oneapi-compiler-dpcpp-cpp-2025.3 \
+    intel-oneapi-mkl-devel-2025.3 \
+    intel-oneapi-dnnl-devel-2025.3 && \
+    rm -rf /var/lib/apt/lists/*
 
 # Install UMD with fixed version
 RUN mkdir neo && \
@@ -52,9 +65,9 @@ RUN curl -LsSf https://astral.sh/uv/install.sh | sh
 RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
 
-# This oneccl contains the BMG support which is not the case for default version of oneapi 2025.2.
-ARG ONECCL_INSTALLER="intel-oneccl-2021.15.7.8_offline.sh"
-RUN wget "https://github.com/uxlfoundation/oneCCL/releases/download/2021.15.7/${ONECCL_INSTALLER}" && \
+# This oneccl contains the BMG support which is not the case for default version of oneapi 2025.3.
+ARG ONECCL_INSTALLER="intel-oneccl-2021.15.9.14_offline.sh"
+RUN wget "https://github.com/uxlfoundation/oneCCL/releases/download/2021.15.9/${ONECCL_INSTALLER}" && \
     bash "${ONECCL_INSTALLER}" -a --silent --eula accept && \
     rm "${ONECCL_INSTALLER}" && \
     echo "source /opt/intel/oneapi/setvars.sh --force" >> /root/.bashrc && \
@@ -66,6 +79,7 @@ SHELL ["bash", "-c"]
 CMD ["bash", "-c", "source /root/.bashrc && exec bash"]
 
 WORKDIR /workspace/
+
 ENV UV_HTTP_TIMEOUT=500
 
 # Configure package index for XPU
@@ -80,18 +94,12 @@ WORKDIR /workspace/vllm
 
 RUN --mount=type=cache,target=/root/.cache/uv \
     uv pip install --upgrade pip && \
-    uv pip install -r requirements/xpu.txt
-
- # used for suffix method speculative decoding
- # build deps for proto + nanobind-based extensions to set up the build environment
-RUN --mount=type=cache,target=/root/.cache/uv \
-    uv pip install grpcio-tools protobuf nanobind
- # arctic-inference is built from source which needs torch-xpu properly installed first
-RUN --mount=type=cache,target=/root/.cache/uv \
+    uv pip install -r requirements/xpu.txt && \
+    uv pip install setuptools_scm &&\
+    uv pip install grpcio-tools protobuf nanobind && \
     source /opt/intel/oneapi/setvars.sh --force && \
     source /opt/intel/oneapi/ccl/2021.15/env/vars.sh --force && \
-    export CMAKE_PREFIX_PATH="$(python -c 'import site; print(site.getsitepackages()[0])'):${CMAKE_PREFIX_PATH}" && \
-    uv pip install --no-build-isolation arctic-inference==0.1.1
+    export CMAKE_PREFIX_PATH="$(python3 -c 'import site; print(site.getsitepackages()[0])'):${CMAKE_PREFIX_PATH}"
 
 ENV LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/"
 
@@ -105,6 +113,9 @@ CMD ["/bin/bash"]
 
 FROM vllm-base AS vllm-openai
 
+# install nixl from source code
+RUN uv pip install nixl
+
 # install additional dependencies for openai api server
 RUN --mount=type=cache,target=/root/.cache/uv \
     uv pip install accelerate hf_transfer pytest pytest_asyncio lm_eval[api] modelscope
@@ -112,10 +123,6 @@ RUN --mount=type=cache,target=/root/.cache/uv \
 # install development dependencies (for testing)
 RUN uv pip install -e tests/vllm_test_utils
 
-# install nixl from source code
-ENV NIXL_VERSION=0.7.0
-RUN python /workspace/vllm/tools/install_nixl_from_source_ubuntu.py
-
 # ensure vllm is properly installed
 RUN python -c "import vllm, inspect; print(vllm.__file__)"
 RUN uv pip show vllm
@@ -135,7 +142,7 @@ RUN uv pip install --no-cache-dir ".[dev]" --no-build-isolation
 # FIX triton
 RUN --mount=type=cache,target=/root/.cache/uv \
     uv pip uninstall triton triton-xpu && \
-    uv pip install triton-xpu==3.6.0
+    uv pip install triton-xpu==3.7.0
 
 # remove torch bundled oneccl to avoid conflicts
 RUN --mount=type=cache,target=/root/.cache/uv \

vllm_omni/diffusion/offloader/sequential_backend.py

@@ -76,10 +76,14 @@ class SequentialOffloadHook(ModelHook):
         if param.device.type == "cpu":
             return
 
+        # XPU's allocator doesn't respect stream dependencies in empty_cache,
+        # so non-blocking copies can race with cache eviction. Use blocking
+        # copies on XPU to avoid NULL pointer errors during DMA.
+        non_blocking = not self.use_hsdp and not current_omni_platform.is_xpu()
         self._move_params(
             module,
             torch.device("cpu"),
-            non_blocking=not self.use_hsdp,
+            non_blocking=non_blocking,
             pin_memory=self.pin_memory,
         )
         current_omni_platform.empty_cache()