Installation with XPU#

vLLM initially supports basic model inferencing and serving on Intel GPU platform.

Table of contents:

  1. Requirements

  2. Quick start using Dockerfile

  3. Build from source

Requirements#

  • OS: Linux

  • Supported Hardware: Intel Data Center GPU (Intel ARC GPU WIP)

  • OneAPI requirements: oneAPI 2024.1

Quick start using Dockerfile#

$ docker build -f Dockerfile.xpu -t vllm-xpu-env --shm-size=4g .
$ docker run -it \
             --rm \
             --network=host \
             --device /dev/dri \
             -v /dev/dri/by-path:/dev/dri/by-path \
             vllm-xpu-env

Build from source#

  • First, install required driver and intel OneAPI 2024.1 or later.

  • Second, install Python packages for vLLM XPU backend building:

$ source /opt/intel/oneapi/setvars.sh
$ pip install --upgrade pip
$ pip install -v -r requirements-xpu.txt

  • Finally, build and install vLLM XPU backend:

$ VLLM_TARGET_DEVICE=xpu python setup.py install

Note

  • FP16 is the default data type in the current XPU backend. The BF16 data type will be supported in the future.