Skip to content

vLLM Ascend

Overview

vllm-project/vllm-ascend

Getting Started¶

Welcome to the vLLM Ascend Plugin! This section will help you get up and running quickly.

Quick Start — Get started with a minimal example
Installation — Install vLLM and vLLM Ascend
Model Tutorials — Step-by-step guides for running specific models
Feature Tutorials — Explore advanced features like PD disaggregation, context parallel, and more
FAQs — Frequently asked questions

What is vLLM Ascend?¶

vLLM Ascend plugin (vllm-ascend) is a community-maintained hardware plugin for running vLLM on the Ascend NPU. It provides a hardware-pluggable interface that decouples the integration of the Ascend NPU with vLLM, enabling popular open-source models to run seamlessly on Ascend hardware.