Merge branch 'main' into stagecli

Author: hsliuustc0106

.buildkite/pipeline.yml

@@ -139,41 +139,41 @@ steps:
             - "/fsx/hf_cache:/fsx/hf_cache"
 
 
-  - label: "Benchmark&Engine Test"
-    timeout_in_minutes: 15
-    depends_on: image-build
-    commands:
-      - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-      - pytest -s -v tests/benchmarks/test_serve_cli.py
-      - pytest -s -v tests/engine/test_async_omni_engine_abort.py
-    agents:
-      queue: "mithril-h100-pool"
-    plugins:
-      - kubernetes:
-          podSpec:
-            containers:
-              - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-                resources:
-                  limits:
-                    nvidia.com/gpu: 2
-                volumeMounts:
-                  - name: devshm
-                    mountPath: /dev/shm
-                  - name: hf-cache
-                    mountPath: /root/.cache/huggingface
-                env:
-                  - name: HF_HOME
-                    value: /root/.cache/huggingface
-            nodeSelector:
-              node.kubernetes.io/instance-type: gpu-h100-sxm
-            volumes:
-              - name: devshm
-                emptyDir:
-                  medium: Memory
-              - name: hf-cache
-                hostPath:
-                  path: /mnt/hf-cache
-                  type: DirectoryOrCreate
+  # - label: "Benchmark&Engine Test"
+  #   timeout_in_minutes: 15
+  #   depends_on: image-build
+  #   commands:
+  #     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  #     - pytest -s -v tests/benchmarks/test_serve_cli.py
+  #     - pytest -s -v tests/engine/test_async_omni_engine_abort.py
+  #   agents:
+  #     queue: "mithril-h100-pool"
+  #   plugins:
+  #     - kubernetes:
+  #         podSpec:
+  #           containers:
+  #             - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+  #               resources:
+  #                 limits:
+  #                   nvidia.com/gpu: 2
+  #               volumeMounts:
+  #                 - name: devshm
+  #                   mountPath: /dev/shm
+  #                 - name: hf-cache
+  #                   mountPath: /root/.cache/huggingface
+  #               env:
+  #                 - name: HF_HOME
+  #                   value: /root/.cache/huggingface
+  #           nodeSelector:
+  #             node.kubernetes.io/instance-type: gpu-h100-sxm
+  #           volumes:
+  #             - name: devshm
+  #               emptyDir:
+  #                 medium: Memory
+  #             - name: hf-cache
+  #               hostPath:
+  #                 path: /mnt/hf-cache
+  #                 type: DirectoryOrCreate
 
   - label: "Omni Model Test"
     timeout_in_minutes: 15
@@ -194,42 +194,42 @@ steps:
           volumes:
             - "/fsx/hf_cache:/fsx/hf_cache"
 
-  - label: "Omni Model Test with H100"
-    timeout_in_minutes: 20
-    depends_on: image-build
-    commands:
-       - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-       - export VLLM_TEST_CLEAN_GPU_MEMORY="1"
-       - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py
-       - pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py -m "core_model" --run-level "core_model"
-    agents:
-       queue: "mithril-h100-pool"
-    plugins:
-       - kubernetes:
-           podSpec:
-             containers:
-               - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-                 resources:
-                   limits:
-                     nvidia.com/gpu: 2
-                 volumeMounts:
-                   - name: devshm
-                     mountPath: /dev/shm
-                   - name: hf-cache
-                     mountPath: /root/.cache/huggingface
-                 env:
-                   - name: HF_HOME
-                     value: /root/.cache/huggingface
-             nodeSelector:
-               node.kubernetes.io/instance-type: gpu-h100-sxm
-             volumes:
-               - name: devshm
-                 emptyDir:
-                   medium: Memory
-               - name: hf-cache
-                 hostPath:
-                   path: /mnt/hf-cache
-                   type: DirectoryOrCreate
+  # - label: "Omni Model Test with H100"
+  #   timeout_in_minutes: 20
+  #   depends_on: image-build
+  #   commands:
+  #      - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  #      - export VLLM_TEST_CLEAN_GPU_MEMORY="1"
+  #      - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py
+  #      - pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py -m "core_model" --run-level "core_model"
+  #   agents:
+  #      queue: "mithril-h100-pool"
+  #   plugins:
+  #      - kubernetes:
+  #          podSpec:
+  #            containers:
+  #              - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+  #                resources:
+  #                  limits:
+  #                    nvidia.com/gpu: 2
+  #                volumeMounts:
+  #                  - name: devshm
+  #                    mountPath: /dev/shm
+  #                  - name: hf-cache
+  #                    mountPath: /root/.cache/huggingface
+  #                env:
+  #                  - name: HF_HOME
+  #                    value: /root/.cache/huggingface
+  #            nodeSelector:
+  #              node.kubernetes.io/instance-type: gpu-h100-sxm
+  #            volumes:
+  #              - name: devshm
+  #                emptyDir:
+  #                  medium: Memory
+  #              - name: hf-cache
+  #                hostPath:
+  #                  path: /mnt/hf-cache
+  #                  type: DirectoryOrCreate
 
   - label: "Qwen3-TTS E2E Test"
     timeout_in_minutes: 20
@@ -251,40 +251,40 @@ steps:
           volumes:
             - "/fsx/hf_cache:/fsx/hf_cache"
 
-  - label: "Diffusion Image Edit Test with H100 (1 GPU)"
-    timeout_in_minutes: 20
-    depends_on: image-build
-    commands:
-      - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-      - pytest -s -v tests/e2e/online_serving/test_image_gen_edit.py
-    agents:
-      queue: "mithril-h100-pool"
-    plugins:
-      - kubernetes:
-          podSpec:
-            containers:
-              - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-                resources:
-                  limits:
-                    nvidia.com/gpu: 1
-                volumeMounts:
-                  - name: devshm
-                    mountPath: /dev/shm
-                  - name: hf-cache
-                    mountPath: /root/.cache/huggingface
-                env:
-                  - name: HF_HOME
-                    value: /root/.cache/huggingface
-            nodeSelector:
-              node.kubernetes.io/instance-type: gpu-h100-sxm
-            volumes:
-              - name: devshm
-                emptyDir:
-                  medium: Memory
-              - name: hf-cache
-                hostPath:
-                  path: /mnt/hf-cache
-                  type: DirectoryOrCreate
+  # - label: "Diffusion Image Edit Test with H100 (1 GPU)"
+  #   timeout_in_minutes: 20
+  #   depends_on: image-build
+  #   commands:
+  #     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+  #     - pytest -s -v tests/e2e/online_serving/test_image_gen_edit.py
+  #   agents:
+  #     queue: "mithril-h100-pool"
+  #   plugins:
+  #     - kubernetes:
+  #         podSpec:
+  #           containers:
+  #             - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+  #               resources:
+  #                 limits:
+  #                   nvidia.com/gpu: 1
+  #               volumeMounts:
+  #                 - name: devshm
+  #                   mountPath: /dev/shm
+  #                 - name: hf-cache
+  #                   mountPath: /root/.cache/huggingface
+  #               env:
+  #                 - name: HF_HOME
+  #                   value: /root/.cache/huggingface
+  #           nodeSelector:
+  #             node.kubernetes.io/instance-type: gpu-h100-sxm
+  #           volumes:
+  #             - name: devshm
+  #               emptyDir:
+  #                 medium: Memory
+  #             - name: hf-cache
+  #               hostPath:
+  #                 path: /mnt/hf-cache
+  #                 type: DirectoryOrCreate
 
   # - label: "Bagel Text2Img Model Test with H100"
   #   timeout_in_minutes: 30

.buildkite/test-nightly.yaml

@@ -5,8 +5,8 @@ steps:
     if: build.env("NIGHTLY") == "1"
     commands:
       - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-      - pytest -s -v tests/e2e/online_serving/test_qwen3_omni_expansion.py
-      - pytest -s -v tests/examples/online_serving/test_qwen3_omni.py
+      - pytest -s -v tests/e2e/online_serving/test_qwen3_omni_expansion.py -m "advanced_model" --run-level "advanced_model"
+      - pytest -s -v tests/examples/online_serving/test_qwen3_omni.py -m "advanced_model" --run-level "advanced_model"
     agents:
       queue: "mithril-h100-pool"
     plugins:
@@ -43,7 +43,7 @@ steps:
     commands:
       - export VLLM_LOGGING_LEVEL=DEBUG
       - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-      - pytest -s -v tests/examples/online_serving/test_qwen2_5_omni.py
+      - pytest -s -v tests/examples/online_serving/test_qwen2_5_omni.py -m "advanced_model" --run-level "advanced_model"
     agents:
       queue: "gpu_4_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
     plugins:

docker/Dockerfile.xpu

@@ -0,0 +1,139 @@
+# Argument to configure vllm base image if pre-built
+ARG VLLM_BASE=vllm-base
+
+FROM intel/deep-learning-essentials:2025.3.2-0-devel-ubuntu24.04 AS vllm-base
+
+WORKDIR /workspace/
+
+ARG PYTHON_VERSION=3.12
+ARG PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/xpu"
+
+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 && \
+    add-apt-repository -y ppa:kobuk-team/intel-graphics
+
+RUN apt clean && apt-get update -y && \
+    apt-get install -y --no-install-recommends --fix-missing \
+    curl \
+    ffmpeg \
+    git \
+    libsndfile1 \
+    libsm6 \
+    libxext6 \
+    libgl1 \
+    lsb-release \
+    libaio-dev \
+    numactl \
+    wget \
+    vim \
+    python3.12 \
+    python3.12-dev \
+    python3-pip
+
+RUN apt update && apt upgrade -y && \
+    apt install -y libze1 libze-dev libze-intel-gpu1 intel-opencl-icd libze-intel-gpu-raytracing intel-ocloc && \
+    apt install -y intel-oneapi-compiler-dpcpp-cpp-2025.3
+
+ENV PATH="/root/.local/bin:$PATH"
+ENV VIRTUAL_ENV="/opt/venv"
+ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
+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}" && \
+    bash "${ONECCL_INSTALLER}" -a --silent --eula accept && \
+    rm "${ONECCL_INSTALLER}" && \
+    echo "source /opt/intel/oneapi/setvars.sh --force" >> /root/.bashrc && \
+    echo "source /opt/intel/oneapi/ccl/2021.15/env/vars.sh --force" >> /root/.bashrc
+RUN rm -f /opt/intel/oneapi/ccl/latest && \
+    ln -s /opt/intel/oneapi/ccl/2021.15 /opt/intel/oneapi/ccl/latest
+
+SHELL ["bash", "-c"]
+CMD ["bash", "-c", "source /root/.bashrc && exec bash"]
+
+WORKDIR /workspace/
+ENV UV_HTTP_TIMEOUT=500
+
+# Configure package index for XPU
+ENV PIP_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
+ENV UV_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
+ENV UV_INDEX_STRATEGY="unsafe-best-match"
+ENV UV_LINK_MODE="copy"
+
+ARG VLLM_VERSION=v0.16.0
+RUN git clone -b ${VLLM_VERSION} https://github.com/vllm-project/vllm
+WORKDIR /workspace/vllm
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv pip install --upgrade pip && \
+    uv pip install -r requirements/xpu.txt
+
+ # used for suffix method speculative decoding
+ # build deps for proto + nanobind-based extensions to set up the build environment
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv pip install grpcio-tools protobuf nanobind
+ # arctic-inference is built from source which needs torch-xpu properly installed first
+RUN --mount=type=cache,target=/root/.cache/uv \
+    source /opt/intel/oneapi/setvars.sh --force && \
+    source /opt/intel/oneapi/ccl/2021.15/env/vars.sh --force && \
+    export CMAKE_PREFIX_PATH="$(python -c 'import site; print(site.getsitepackages()[0])'):${CMAKE_PREFIX_PATH}" && \
+    uv pip install --no-build-isolation arctic-inference==0.1.1
+
+ENV LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/"
+
+ENV VLLM_TARGET_DEVICE=xpu
+ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv pip install --no-build-isolation .
+
+CMD ["/bin/bash"]
+
+FROM vllm-base AS vllm-openai
+
+# 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
+
+# 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
+
+CMD ["/bin/bash"]
+
+ENTRYPOINT []
+
+FROM ${VLLM_BASE} AS vllm-omni
+
+WORKDIR /workspace/vllm-omni
+COPY . .
+
+ENV VLLM_OMNI_TARGET_DEVICE=xpu
+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
+
+# remove torch bundled oneccl to avoid conflicts
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv pip uninstall oneccl oneccl-devel
+
+FROM vllm-omni AS vllm-omni-openai
+
+RUN ln -sf /usr/bin/python3 /usr/bin/python
+
+ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
+
+ENTRYPOINT ["vllm", "serve", "--omni"]

docs/getting_started/installation/README.md

@@ -5,4 +5,5 @@ vLLM-Omni supports the following hardware platforms:
 - [GPU](gpu.md)
     - [NVIDIA CUDA](gpu.md)
     - [AMD ROCm](gpu.md)
+    - [Intel XPU](gpu.md)
 - [NPU](npu.md)