(installation-index)=

# Installation

vLLM supports the following hardware platforms:

:::{toctree}
:maxdepth: 1
:hidden:

gpu/index
cpu/index
ai_accelerator/index
:::

- <project:gpu/index.md>
  - NVIDIA CUDA
  - AMD ROCm
  - Intel XPU
- <project:cpu/index.md>
  - Intel/AMD x86
  - ARM AArch64
  - Apple silicon
- <project:ai_accelerator/index.md>
  - Google TPU
  - Intel Gaudi
  - AWS Neuron
  - OpenVINO