[Hardware][Intel GPU] upgrade IPEX dependency to 2.6.10. (#14564)

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

Dockerfile.xpu

@@ -1,4 +1,4 @@
-FROM intel/oneapi-basekit:2024.2.1-0-devel-ubuntu22.04 AS vllm-base
+FROM intel/deep-learning-essentials:2025.0.1-0-devel-ubuntu22.04 AS vllm-base
 
 RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/intel-oneapi-archive-keyring.gpg > /dev/null && \
     echo "deb [signed-by=/usr/share/keyrings/intel-oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main " | tee /etc/apt/sources.list.d/oneAPI.list && \
@@ -21,7 +21,8 @@ RUN apt-get update -y && \
     python3 \
     python3-dev \
     python3-pip \
-    # vim \
+    libze-intel-gpu-dev \
+    libze-intel-gpu1 \
     wget
 
 WORKDIR /workspace/vllm
@@ -32,19 +33,10 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     pip install --no-cache-dir \
     -r requirements/xpu.txt
 
-RUN git clone https://github.com/intel/pti-gpu && \
-    cd pti-gpu/sdk && \
-    git checkout 6c491f07a777ed872c2654ca9942f1d0dde0a082 && \
-    mkdir build && \
-    cd build && \
-    cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_TOOLCHAIN_FILE=../cmake/toolchains/icpx_toolchain.cmake -DBUILD_TESTING=OFF .. && \
-    make -j && \
-    cmake --install . --config Release --prefix "/usr/local"
-
 ENV LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/"
 
 COPY . .
-ARG GIT_REPO_CHECK
+ARG GIT_REPO_CHECK=0
 RUN --mount=type=bind,source=.git,target=.git \
     if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh; fi
 
@@ -54,6 +46,12 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     --mount=type=bind,source=.git,target=.git \
     python3 setup.py install
 
+# Please refer xpu doc, we need manually install intel-extension-for-pytorch 2.6.10+xpu due to there are some conflict dependencies with torch 2.6.0+xpu
+# FIXME: This will be fix in ipex 2.7. just leave this here for awareness.
+RUN --mount=type=cache,target=/root/.cache/pip \
+    pip install intel-extension-for-pytorch==2.6.10+xpu \
+    --extra-index-url=https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
+
 CMD ["/bin/bash"]
 
 FROM vllm-base AS vllm-openai

docs/source/getting_started/installation/gpu/xpu.inc.md

@@ -9,7 +9,7 @@ There are no pre-built wheels or images for this device, so you must build vLLM
 ## Requirements
 
 - Supported Hardware: Intel Data Center GPU, Intel ARC GPU
-- OneAPI requirements: oneAPI 2024.2
+- OneAPI requirements: oneAPI 2025.0
 
 ## Set up using Python
 
@@ -19,21 +19,27 @@ Currently, there are no pre-built XPU wheels.
 
 ### Build wheel from source
 
-- First, install required driver and intel OneAPI 2024.2 or later.
+- First, install required driver and Intel OneAPI 2025.0 or later.
 - Second, install Python packages for vLLM XPU backend building:
 
 ```console
-source /opt/intel/oneapi/setvars.sh
 pip install --upgrade pip
 pip install -v -r requirements/xpu.txt
 ```
 
-- Finally, build and install vLLM XPU backend:
+- Then, build and install vLLM XPU backend:
 
 ```console
 VLLM_TARGET_DEVICE=xpu python setup.py install
 ```
 
+- Finally, due to a known issue of conflict dependency(oneapi related) in torch-xpu 2.6 and ipex-xpu 2.6, we install ipex here. This will be fixed in the ipex-xpu 2.7.
+
+```console
+pip install intel-extension-for-pytorch==2.6.10+xpu \
+    --extra-index-url=https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
+```
+
 :::{note}
 - FP16 is the default data type in the current XPU backend. The BF16 data
   type is supported on Intel Data Center GPU, not supported on Intel Arc GPU yet.
@@ -59,7 +65,7 @@ $ docker run -it \
 
 ## Supported features
 
-XPU platform supports tensor-parallel inference/serving and also supports pipeline parallel as a beta feature for online serving. We requires Ray as the distributed runtime backend. For example, a reference execution likes following:
+XPU platform supports **tensor parallel** inference/serving and also supports **pipeline parallel** as a beta feature for online serving. We requires Ray as the distributed runtime backend. For example, a reference execution likes following:
 
 ```console
 python -m vllm.entrypoints.openai.api_server \
@@ -73,3 +79,5 @@ python -m vllm.entrypoints.openai.api_server \
 ```
 
 By default, a ray instance will be launched automatically if no existing one is detected in system, with `num-gpus` equals to `parallel_config.world_size`. We recommend properly starting a ray cluster before execution, referring to the <gh-file:examples/online_serving/run_cluster.sh> helper script.
+
+There are some new features coming with ipex-xpu 2.6, eg: **chunked prefill**, **V1 engine support**, **lora**, **MoE**, etc.

requirements/xpu.txt

@@ -1,7 +1,7 @@
 # Common dependencies
 -r common.txt
 
-ray >= 2.9
+ray>=2.9
 cmake>=3.26
 ninja
 packaging
@@ -9,9 +9,16 @@ setuptools-scm>=8
 setuptools>=75.8.0
 wheel
 jinja2
+datasets # for benchmark scripts
 
-torch @ https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/torch-2.5.0a0%2Bgite84e33f-cp310-cp310-linux_x86_64.whl
-intel-extension-for-pytorch @ https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/intel_extension_for_pytorch-2.5.10%2Bgit9d489a8-cp310-cp310-linux_x86_64.whl
-oneccl_bind_pt @ https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/oneccl_bind_pt-2.5.0%2Bxpu-cp310-cp310-linux_x86_64.whl
+torch==2.6.0+xpu
+torchaudio
+torchvision
+pytorch-triton-xpu
+--extra-index-url=https://download.pytorch.org/whl/xpu
 
-triton-xpu == 3.0.0b1
+# Please refer xpu doc, we need manually install intel-extension-for-pytorch 2.6.10+xpu due to there are some conflict dependencies with torch 2.6.0+xpu
+# FIXME: This will be fix in ipex 2.7. just leave this here for awareness.
+# intel-extension-for-pytorch==2.6.10+xpu
+oneccl_bind_pt==2.6.0+xpu
+--extra-index-url=https://pytorch-extension.intel.com/release-whl/stable/xpu/us/