# vllm-project/vllm-ascend

> A hardware plugin for vLLM that runs LLM inference on Ascend NPUs (Atlas A2/A3). It enables deployment of Transformer, MoE, embedding and multimodal models on Huawei Ascend hardware.

- Magnitude: 0.8 out of 10 — Steady
- Stars: 2,918 total · +0 stars on 2026-10-02 (UTC), ≈ 1 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2025-01-29 · Last push: 2026-10-01
- GitHub: https://github.com/vllm-project/vllm-ascend · Homepage: https://docs.vllm.ai/projects/ascend · Page: https://gitnova.dev/en/r/vllm-project/vllm-ascend

## Useful for

- Serve LLMs on an Atlas A2 cluster via vLLM
- Deploy a multimodal or MoE model on Ascend NPUs
- Set up large-scale Expert Parallelism for big MoE models

## Why it’s here

- A steady background without notable changes.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 2,387
- Issues and pull requests: 17,848
- Watchers: 75
- Average over the last week: 4 per day
- Usual pace: 7 per day
- Latest release: v0.27.1rc1 (2026-09-29)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 2, 2, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

09-19 1.8, 09-20 1.4, 09-21 1.7, 09-22 1.8, 09-23 1.9, 09-24 1.8, 09-25 1.5, 09-26 1.2, 09-27 0.7, 09-28 1.4, 09-29 2.0, 09-30 1.8, 10-01 1.2, 10-02 1.1

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-02 10:18 UTC, updated every 30 minutes.