[XPU][Doc] Update XPU docker image documents (#49148)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Kunshang Ji committed
Jul 21, 2026 at 10:11 UTC
e78a0c8e5965a8bbe76c047a1cff99e1a5974276
3 files changed
+44
-2
README.md
+1
-1
@@ -48,7 +48,7 @@ vLLM is flexible and easy to use with:
48
- Tool calling and reasoning parsers
49
- OpenAI-compatible API server, plus Anthropic Messages API and gRPC support
50
- Efficient multi-LoRA support for dense and MoE layers
51
-- Support for NVIDIA GPUs, AMD GPUs, and x86/ARM/PowerPC CPUs. Additionally, diverse hardware plugins such as Google TPUs, Intel Gaudi, IBM Spyre, Huawei Ascend, Rebellions NPU, Apple Silicon, MetaX GPU, and more.
51
+- Support for NVIDIA GPUs, AMD GPUs, Intel GPUs, and x86/ARM/PowerPC CPUs. Additionally, diverse hardware plugins such as Google TPUs, Intel Gaudi, IBM Spyre, Huawei Ascend, Rebellions NPU, Apple Silicon, MetaX GPU, and more.
52
53
vLLM seamlessly supports 200+ model architectures on Hugging Face, including:
54
docs/getting_started/installation/gpu.xpu.inc.md
+34
-1
@@ -58,7 +58,40 @@ VLLM_TARGET_DEVICE=xpu pip install --no-build-isolation -e . -v
58
--8<-- [end:build-wheel-from-source]
59
--8<-- [start:pre-built-images]
60
61
-Currently, we release prebuilt XPU images at docker [hub](https://hub.docker.com/r/intel/vllm/tags) based on vLLM released version. For more information, please refer release [note](https://github.com/intel/ai-containers/blob/main/vllm).
61
+vLLM offers official Docker images for deployment.
62
+The images can be used to run OpenAI compatible server and are available on Docker Hub as [vllm/vllm-openai-xpu](https://hub.docker.com/r/vllm/vllm-openai-xpu/tags).
63
+
64
+- `vllm/vllm-openai-xpu:latest` — stable release, available starting from v0.26.0
65
+- `vllm/vllm-openai-xpu:nightly` — preview build from the latest development branch, use this if you want the latest features and fixes
66
+
67
+```bash
68
+docker run --rm \
69
+ --network=host \
70
+ --device /dev/dri:/dev/dri \
71
+ -v /dev/dri/by-path:/dev/dri/by-path \
72
+ -v ~/.cache/huggingface:/root/.cache/huggingface \
73
+ --env "HF_TOKEN=$HF_TOKEN" \
74
+ --ipc=host \
75
+ --privileged \
76
+ vllm/vllm-openai-xpu:<tag> \
77
+ --model Qwen/Qwen3-0.6B
78
+```
79
+
80
+To use the docker image as base for development, you can launch it in interactive session through overriding the entrypoint.
81
+
82
+???+ console "Commands"
83
+ ```bash
84
+ docker run --rm -it \
85
+ --network=host \
86
+ --device /dev/dri:/dev/dri \
87
+ -v /dev/dri/by-path:/dev/dri/by-path \
88
+ -v ~/.cache/huggingface:/root/.cache/huggingface \
89
+ --env "HF_TOKEN=$HF_TOKEN" \
90
+ --ipc=host \
91
+ --privileged \
92
+ --entrypoint /bin/bash \
93
+ vllm/vllm-openai-xpu:<tag>
94
+ ```
95
96
--8<-- [end:pre-built-images]
97
--8<-- [start:build-image-from-source]
docs/getting_started/quickstart.md
+9
@@ -65,6 +65,15 @@ This guide will help you quickly get started with vLLM to perform:
65
!!! tip
66
A nightly Docker image is also available as [vllm/vllm-openai-rocm:nightly](https://hub.docker.com/r/vllm/vllm-openai-rocm/tags) for testing the latest development builds.
67
68
+=== "Intel GPU"
69
+
70
+ vLLM supports Intel GPUs through the XPU backend. Pre-built XPU wheels will be available soon.
71
+
72
+ Official Docker images for Intel GPUs are added to the vLLM release starting from v0.26.0. Nightly Docker image is also available as [vllm/vllm-openai-xpu:nightly](https://hub.docker.com/r/vllm/vllm-openai-xpu/tags).
73
+
74
+ !!! tip
75
+ For more detailed instructions, including building from source and Docker image setup, please refer to the [GPU installation guide](installation/gpu.md) and select the "Intel XPU" tab.
76
+
77
=== "Google TPU"
78
79
To run vLLM on Google TPUs, you need to install the `vllm-tpu` package.