LM/vLLM

Experiment

uv venv --python 3.12 --seed --managed-python
source .venv/bin/activate

git clone https://github.com/vllm-project/vllm.git
cd vllm
pip install --upgrade pip
pip install -v -r requirements/xpu.txt

pip uninstall -y triton triton-xpu
pip install triton-xpu==3.7.2 --extra-index-url https://download.pytorch.org/whl/xpu

VLLM_TARGET_DEVICE=xpu pip install --no-build-isolation -e . -v

# check device
python -c "import torch; print(torch.xpu.is_available()); print(torch.xpu.device_count())"

# download model
hf download ciocan/gemma-4-E4B-it-W4A16

# Run
vllm serve unsloth/gemma-4-E4B-it-qat-GGUF --device xpu

Path

TODO

• https://hub.docker.com/r/intel/vllm
• https://hub.docker.com/u/intel/?page=1&search=vllm
• https://docs.vllm.ai/en/stable/getting_started/installation/gpu/#requirements
• https://www.pugetsystems.com/labs/articles/intel-arc-pro-b70-multi-gpu-ai-inference-performance/
• https://github.com/Hal9000AIML/arc-pro-b70-inference-setup-ubuntu-server
• https://sergiiob.dev/posts/intel-arc-b70-vllm-initial-mxfp4-test/
• https://forum.level1techs.com/t/intel-b70-launch-unboxed-and-tested/247873
• https://huggingface.co/blog/MatrixYao/intel-gpu