[XPU][CI] Fix xpu after rebasing for 0.25.0 (#5066)

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

.buildkite/pipeline-intel.yaml

@@ -10,7 +10,7 @@ steps:
           DOCKER_BUILDKIT: "1"
           # Buildkite will automatically replace this with the actual commit hash
           VLLM_IMAGE_TAG: "${BUILDKITE_COMMIT}"
-          VLLM_VERSION: "v0.24.0"
+          VLLM_VERSION: "v0.25.0"
         priority: 100
         timeout_in_minutes: 60
         soft_fail: false

.buildkite/scripts/hardware_ci/run-xpu-test.sh

@@ -13,12 +13,33 @@ container_name="xpu_${BUILDKITE_COMMIT}_$(
 )"
 
 cd "${omni_source_dir}"
+
+# The XPU base image is ~37GB; the default gzip layer exporter is single-threaded
+# and takes ~16min to compress it. zstd is multi-threaded (uses all cores) at a
+# similar ratio; set EXPORT_COMPRESSION=uncompressed to skip compression entirely
+# for local-only images. This requires the containerd image store (buildx docker
+# driver), which is the default here.
+EXPORT_COMPRESSION="${EXPORT_COMPRESSION:-zstd}"
+if [ "${EXPORT_COMPRESSION}" = "uncompressed" ]; then
+    export_args=(--output "type=image,name={{IMAGE}},compression=uncompressed")
+else
+    export_args=(--output "type=image,name={{IMAGE}},compression=${EXPORT_COMPRESSION},compression-level=3,force-compression=true")
+fi
+
+docker_build() {
+    # $1 = image name; remaining args passed through to docker build.
+    local image="$1"
+    shift
+    local out=("${export_args[@]/'{{IMAGE}}'/${image}}")
+    docker build "${out[@]}" "$@" -f docker/Dockerfile.xpu .
+}
+
 if [ -z "$(docker images -q "${base_image_name}")" ]; then
-    docker build --target vllm-base -t "${base_image_name}" --build-arg "VLLM_VERSION=${VLLM_VERSION}" -f docker/Dockerfile.xpu .
+    docker_build "${base_image_name}" --target vllm-base --build-arg "VLLM_VERSION=${VLLM_VERSION}"
 fi
 
 # Try building the docker image
-docker build --build-arg "VLLM_BASE=${base_image_name}" --build-arg "VLLM_VERSION=${VLLM_VERSION}" -t "${image_name}" -f docker/Dockerfile.xpu .
+docker_build "${image_name}" --build-arg "VLLM_BASE=${base_image_name}" --build-arg "VLLM_VERSION=${VLLM_VERSION}"
 
 # Setup cleanup
 remove_docker_container() {

docker/Dockerfile.xpu

@@ -88,7 +88,7 @@ ENV UV_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
 ENV UV_INDEX_STRATEGY="unsafe-best-match"
 ENV UV_LINK_MODE="copy"
 
-ARG VLLM_VERSION=v0.24.0
+ARG VLLM_VERSION=v0.25.0
 RUN git clone -b ${VLLM_VERSION} https://github.com/vllm-project/vllm
 WORKDIR /workspace/vllm
 

tests/platforms/test_cuda_ir_op_priority.py

@@ -3,8 +3,17 @@
 
 import pytest
 from vllm.config import CompilationConfig, CompilationMode, DeviceConfig, VllmConfig
+from vllm.platforms import current_platform
 
-from vllm_omni.platforms.cuda.platform import CudaOmniPlatform
+# Importing CudaOmniPlatform pulls in vllm.platforms.cuda, which imports the
+# CUDA-only ``vllm._C_stable_libtorch`` extension at module top level. That
+# extension is absent on non-CUDA builds (e.g. XPU), so skip the whole module
+# there before the import can crash collection. ``is_cuda()`` resolves the
+# platform without importing cuda.py.
+if not current_platform.is_cuda():
+    pytest.skip("CUDA-only IR op priority tests", allow_module_level=True)
+
+from vllm_omni.platforms.cuda.platform import CudaOmniPlatform  # noqa: E402
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]