2025-11-30 20:39:06 +08:00
|
|
|
# NPU
|
2025-11-28 11:03:52 +08:00
|
|
|
|
2025-11-30 20:39:06 +08:00
|
|
|
vLLM-Omni supports NPU through the vLLM Ascend Plugin (vllm-ascend). This is a community maintained hardware plugin for running vLLM on NPU.
|
|
|
|
|
|
|
|
|
|
## Requirements
|
|
|
|
|
|
|
|
|
|
- OS: Linux
|
|
|
|
|
- Python: 3.12
|
|
|
|
|
|
|
|
|
|
!!! note
|
|
|
|
|
vLLM-Omni is currently not natively supported on Windows.
|
|
|
|
|
|
|
|
|
|
=== "NPU"
|
|
|
|
|
|
|
|
|
|
--8<-- "docs/getting_started/installation/npu/npu.inc.md:requirements"
|
|
|
|
|
|
|
|
|
|
## Installation
|
|
|
|
|
|
2026-02-04 15:10:50 +08:00
|
|
|
### Set up using Docker
|
|
|
|
|
|
|
|
|
|
=== "NPU"
|
|
|
|
|
|
|
|
|
|
--8<-- "docs/getting_started/installation/npu/npu.inc.md:pre-built-images"
|
|
|
|
|
|
|
|
|
|
### Build wheel from source
|
2025-11-30 20:39:06 +08:00
|
|
|
|
2026-02-26 14:26:50 +08:00
|
|
|
=== "NPU release"
|
2025-11-30 20:39:06 +08:00
|
|
|
|
2026-02-26 14:26:50 +08:00
|
|
|
--8<-- "docs/getting_started/installation/npu/npu.inc.md:installation-release"
|
|
|
|
|
|
|
|
|
|
=== "NPU from main"
|
|
|
|
|
|
|
|
|
|
--8<-- "docs/getting_started/installation/npu/npu.inc.md:installation-main"
|
