---
title: "vllm-ascend"
type: "tool"
slug: "vllm-project-vllm-ascend"
canonical_url: "https://www.graphcanon.com/tools/vllm-project-vllm-ascend"
github_url: "https://github.com/vllm-project/vllm-ascend"
homepage_url: "https://docs.vllm.ai/projects/ascend"
stars: 2373
forks: 1547
primary_language: "C++"
license: "Apache-2.0"
categories: ["inference-serving"]
tags: ["ascend", "model-serving", "llm-serving", "transformer", "inference"]
updated_at: "2026-07-07T18:44:38.609781+00:00"
---

# vllm-ascend

> Community maintained hardware plugin for vLLM on Ascend

The repository provides a hardware plugin specifically tailored for the vLLM (very Large Language Model) project, designed to enhance the performance and efficiency of large language models when running on Huawei's Ascend AI processors.

## Facts

- Repository: https://github.com/vllm-project/vllm-ascend
- Homepage: https://docs.vllm.ai/projects/ascend
- Stars: 2,373 · Forks: 1,547 · Open issues: 2,323 · Watchers: 33
- Primary language: C++
- License: Apache-2.0
- Last pushed: 2026-07-07T13:55:58+00:00

## Categories

- [Inference & Serving](/categories/inference-serving.md)

## Tags

ascend, model-serving, llm-serving, transformer, inference

## Related tools

- [open-webui](/tools/open-webui-open-webui.md) - User-friendly AI Interface (Supports Ollama, OpenAI API, ...) (★ 144,575)
- [vllm](/tools/vllm-project-vllm.md) - A high-throughput and memory-efficient inference and serving engine for LLMs (★ 85,612)
- [rtk](/tools/rtk-ai-rtk.md) - CLI proxy reducing LLM token consumption by 60-90% (★ 69,253)
- [unsloth](/tools/unslothai-unsloth.md) - Unsloth Studio is a web UI for training and running open models locally. (★ 67,883)
- [anything-llm](/tools/mintplex-labs-anything-llm.md) - Stop renting your intelligence. Own it with AnythingLLM. (★ 62,759)
- [mem0](/tools/mem0ai-mem0.md) - Universal memory layer for AI Agents (★ 60,317)
- [litellm](/tools/berriai-litellm.md) - Python SDK and Proxy Server for calling over 100 LLM APIs in OpenAI format (★ 52,877)
- [ray](/tools/ray-project-ray.md) - Unified framework for scaling AI and Python applications (★ 43,153)

## README (excerpt)

```text
<p align="center">
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/vllm-project/vllm-ascend/main/docs/source/logos/vllm-ascend-logo-text-dark.png">
    <img alt="vllm-ascend" src="https://raw.githubusercontent.com/vllm-project/vllm-ascend/main/docs/source/logos/vllm-ascend-logo-text-light.png" width=55%>
  </picture>
</p>

<h3 align="center">
vLLM Ascend Plugin
</h3>

<div align="center">



</div>

<p align="center">
| <a href="https://www.hiascend.com/en/"><b>About Ascend</b></a> | <a href="https://docs.vllm.ai/projects/ascend/en/latest/"><b>Documentation</b></a> | <a href="https://slack.vllm.ai"><b>#SIG-Ascend</b></a> | <a href="https://discuss.vllm.ai/c/hardware-support/vllm-ascend-support"><b>Users Forum</b></a> | <a href="https://tinyurl.com/vllm-ascend-meeting"><b>Weekly Meeting</b></a> |
</p>

<p align="center">
<a ><b>English</b></a> | <a href="README.zh.md"><b>中文</b></a>
</p>

---
*Latest News* 🔥

- [2026/05] We released the new official version [v0.18.0](https://github.com/vllm-project/vllm-ascend/releases/tag/v0.18.0)! Please follow the [official guide](https://docs.vllm.ai/projects/ascend/en/v0.18.0/) to start using vLLM Ascend Plugin on Ascend.
- [2026/02] We released the new official version [v0.13.0](https://github.com/vllm-project/vllm-ascend/releases/tag/v0.13.0)! Please follow the [official guide](https://docs.vllm.ai/projects/ascend/en/v0.13.0/) to start using vLLM Ascend Plugin on Ascend.

<details>
<summary>More</summary>

- [2025/12] We released the new official version [v0.11.0](https://github.com/vllm-project/vllm-ascend/releases/tag/v0.11.0)! Please follow the [official guide](https://docs.vllm.ai/projects/ascend/en/v0.11.0/) to start using vLLM Ascend Plugin on Ascend.
- [2025/09] We released the new official version [v0.9.1](https://github.com/vllm-project/vllm-ascend/releases/tag/v0.9.1)! Please follow the [official guide](https://docs.vllm.ai/projects/ascend/en/v0.9.1/tutorials/large_scale_ep.html) to start deploying large-scale Expert Parallelism (EP) on Ascend.
- [2025/08] We hosted the [vLLM Beijing Meetup](https://mp.weixin.qq.com/s/7n8OYNrCC_I9SJaybHA_-Q) with vLLM and Tencent! Please find the [meetup slides](https://drive.google.com/drive/folders/1Pid6NSFLU43DZRi0EaTcPgXsAzDvbBqF).
- [2025/06] [User stories](https://docs.vllm.ai/projects/ascend/en/latest/community/user_stories/index.html) page is now live! It kicks off with LLaMA-Factory/verl/TRL/GPUStack to demonstrate how vLLM Ascend assists Ascend users in enhancing their experience across fine-tuning, evaluation, reinforcement learning (RL), and deployment scenarios.
- [2025/06] [Contributors](https://docs.vllm.ai/projects/ascend/en/latest/community/contributors.html) page is now live! All contributions deserve to be recorded, thanks for all contributors.
- [2025/05] We've released the first official version [v0.7.3](https://github.com/vllm-project/vllm-ascend/releases/tag/v0.7.3)! We collaborated with the vLLM community to publish a blog post sharing our practice: [Introducing vLLM Hardware Plugin, Best Practice from Ascend NPU](https://blog.vllm.ai/2025/05/12/hardware-plugin.html).
- [2025/03] We hosted the [vLLM Beijing Meetup](https://mp.weixin.qq.com/s/VtxO9WXa5fC-mKqlxNUJUQ) with vLLM team! Please find the [meetup slides](https://drive.google.com/drive/folders/1Pid6NSFLU43DZRi0EaTcPgXsAzDvbBqF).
- [2025/02] vLLM community officially created [vllm-project/vllm-ascend](https://github.com/vllm-project/vllm-ascend) repo for running vLLM seamlessly on the Ascend NPU.
- [2024/12] We are working with the vLLM community to support [[RFC]: Hardware pluggable](https://github.com/vllm-project/vllm/issues/11162).

</details>

---

## Overview

vLLM Ascend (`vllm-ascend`) is a community maintained hardware plugin for running vLLM seamlessly on the Ascend NPU.

It is the recommended approach for supporting the Ascend backend within the vLLM community. It adheres to the principles outlined i
```

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/tools/vllm-project-vllm-ascend`](/api/graphcanon/tools/vllm-project-vllm-ascend)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_