2025-01-06 10:18:33 +08:00
|
|
|
(installation-index)=
|
|
|
|
|
|
|
|
|
|
# Installation
|
|
|
|
|
|
|
|
|
|
vLLM supports the following hardware platforms:
|
|
|
|
|
|
2025-01-29 03:38:29 +00:00
|
|
|
:::{toctree}
|
2025-01-06 10:18:33 +08:00
|
|
|
:maxdepth: 1
|
2025-01-31 23:38:35 +00:00
|
|
|
:hidden:
|
2025-01-06 10:18:33 +08:00
|
|
|
|
2025-03-10 18:43:08 +01:00
|
|
|
installation/gpu
|
|
|
|
|
installation/cpu
|
|
|
|
|
installation/ai_accelerator
|
2025-01-29 03:38:29 +00:00
|
|
|
:::
|
2025-01-31 23:38:35 +00:00
|
|
|
|
2025-03-10 18:43:08 +01:00
|
|
|
- <project:installation/gpu.md>
|
2025-01-31 23:38:35 +00:00
|
|
|
- NVIDIA CUDA
|
|
|
|
|
- AMD ROCm
|
|
|
|
|
- Intel XPU
|
2025-03-10 18:43:08 +01:00
|
|
|
- <project:installation/cpu.md>
|
2025-01-31 23:38:35 +00:00
|
|
|
- Intel/AMD x86
|
|
|
|
|
- ARM AArch64
|
|
|
|
|
- Apple silicon
|
2025-03-11 22:32:17 +05:30
|
|
|
- IBM Z (S390X)
|
2025-03-10 18:43:08 +01:00
|
|
|
- <project:installation/ai_accelerator.md>
|
2025-01-31 23:38:35 +00:00
|
|
|
- Google TPU
|
|
|
|
|
- Intel Gaudi
|
|
|
|
|
- AWS Neuron
|
