[Bug]: Installation with XPU fail's with Dockerfile and while building from sourcefile

[adi-lb-phoenix]

Your current environment

The output of `python collect_env.py`

The below output is from podman distrobox :
uname -a
Linux ubuntu22vllm.JOHNAIC 6.8.0-40-generic #40~22.04.3-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 30 17:30:19 UTC 2 x86_64 x86_64 x86_64 GNU/Linux

the below output is from the host
Your output of `python collect_env.py` here

Versions of relevant libraries:
[pip3] intel_extension_for_pytorch==2.3.110+xpu
[pip3] numpy==1.26.4
[pip3] nvidia-cublas-cu12==12.1.3.1
[pip3] nvidia-cuda-cupti-cu12==12.1.105
[pip3] nvidia-cuda-nvrtc-cu12==12.1.105
[pip3] nvidia-cuda-runtime-cu12==12.1.105
[pip3] nvidia-cudnn-cu12==8.9.2.26
[pip3] nvidia-cufft-cu12==11.0.2.54
[pip3] nvidia-curand-cu12==10.3.2.106
[pip3] nvidia-cusolver-cu12==11.4.5.107
[pip3] nvidia-cusparse-cu12==12.1.0.106
[pip3] nvidia-nccl-cu12==2.19.3
[pip3] nvidia-nvjitlink-cu12==12.6.68
[pip3] nvidia-nvtx-cu12==12.1.105
[pip3] pyzmq==26.2.0
[pip3] torch==2.3.1+cxx11.abi
[pip3] transformers==4.44.2
[pip3] triton==2.2.0
[pip3] triton-xpu==3.0.0b2
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: N/A
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
Could not collect

Model Input Dumps

No response

🐛 Describe the bug

For installing vllm for linux to execute on intel GPU, we have followed the instructions in https://docs.vllm.ai/en/latest/getting_started/xpu-installation.html#installation-with-xpu .

Case 1 :
We have created a ubuntu image using distrobox on podman. We tried to build from source .
The commands were

pip install --upgrade pip
pip install -v -r requirements-xpu.txt

logfile of the above command
output.txt

 VLLM_TARGET_DEVICE=xpu python setup.py install
error in vllm setup command: 'install_requires' must be a string or list of strings containing valid project/version requirement specifiers; Expected package name at the start of dependency specifier
    --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/

CASE 2:
The below error is when we tried to build using dockerfile on the host system outside podman using the instructions present in https://docs.vllm.ai/en/latest/getting_started/xpu-installation.html#quick-start-using-dockerfile . Instead of docker, we used podman to build it which it failed at.

podman  build -f Dockerfile.xpu -t vllm-xpu-env --shm-size=4g .
STEP 1/9: FROM intel/oneapi-basekit:2024.2.1-0-devel-ubuntu22.04
STEP 2/9: 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 &&     chmod 644 /usr/share/keyrings/intel-oneapi-archive-keyring.gpg &&     wget -O- https://repositories.intel.com/graphics/intel-graphics.key | gpg --dearmor | tee /usr/share/keyrings/intel-graphics.gpg > /dev/null &&     echo "deb [arch=amd64,i386 signed-by=/usr/share/keyrings/intel-graphics.gpg] https://repositories.intel.com/graphics/ubuntu jammy arc" | tee /etc/apt/sources.list.d/intel.gpu.jammy.list &&     chmod 644 /usr/share/keyrings/intel-graphics.gpg
--> Using cache 098758915996e49e32aed0d13aeb3b8df2c91e8fdc5da8fbaa14ff225b08e617
--> 09875891599
STEP 3/9: RUN apt-get update  -y && apt-get install -y curl libicu70 lsb-release git wget vim numactl python3 python3-pip ffmpeg libsm6 libxext6 libgl1 
--> Using cache 829501e9861021f829aea63da9ed910954aed2512b659241f1a1c1498aa22b51
--> 829501e9861
STEP 4/9: RUN git clone https://github.com/intel/pti-gpu &&     cd pti-gpu/sdk &&     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"
--> Using cache be5f38cbc94153cbcec3f5a26186898029a06f485e42460bfcbcd485109336e9
--> be5f38cbc94
STEP 5/9: COPY ./ /workspace/vllm
--> Using cache 5a66d6e91f3297586deab5dcda71c39ee7167bae205fde72fe23918b92c71fd0
--> 5a66d6e91f3
STEP 6/9: WORKDIR /workspace/vllm
--> Using cache 284936c2e4cb04c65775b41cab7aa8d3df76f59fd25eb3d3ecc70af9b947d4d0
--> 284936c2e4c
STEP 7/9: RUN pip install -v -r requirements-xpu.txt
--> Using cache b5c12deac57e71d03e8ed05f892be4ebace345ee2a146b2dec0feb3444831edd
--> b5c12deac57
STEP 8/9: RUN VLLM_TARGET_DEVICE=xpu python3 setup.py install
error in vllm setup command: 'install_requires' must be a string or list of strings containing valid project/version requirement specifiers; Parse error at "'--extra-'": Expected W:(abcd...)
Error: error building at STEP "RUN VLLM_TARGET_DEVICE=xpu python3 setup.py install": error while running runtime: exit status 1

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.