Home/Inference & Serving/vllm-ascend

vllm-ascend

vllm-project/vllm-ascend

Community maintained hardware plugin for vLLM on Ascend

GitHub Website

GraphCanon updated today · GitHub synced today · 38 views this month

2.7k stars2.1k forksLast push today C++ Apache-2.0

Decision brief

vllm-ascend: Ascend hardware plugin for vLLM in C++

Good fit when

You need to optimize large language model inference on Ascend hardware
Your project prioritizes community-driven enhancements and support

Avoid when

If you require support for GPU or CPU only setups without Ascend hardware
When seeking proprietary software, as vllm-ascend is open-source under Apache License 2.0

Observed Jul 12, 2026 · Source: enrich:decision_facts

vllm-ascend alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Very active (0d since push); As of today
Provenance: Not a fork · Organization account; As of today
Security (OSV): 9 low (9 low); As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Backing

Company context for vLLM. Display-only - separate from trust and ranking.

Company: vLLM·GitHub org profile·1mo
Commercial model: Pure OSS·GitHub org profile (public repos)·1mo

Install

git clone https://github.com/vllm-project/vllm-ascend

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

88k★

llmfit

Hundreds of models & providers. One command to find what runs on your hardware.

32k★

omlx

LLM inference server with continuous batching and SSD caching for Apple Silicon

19k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

vllm-project/vllm-ascend is a community-driven project to enhance vLLM's compatibility with Ascend hardware. It aims at optimizing the deployment and inference capabilities of large language models using C++.

Capability facts

Deploy: Self-host
Source: dockerfile:Dockerfile · Aug 20, 2026
Docker: Dockerfile present
Source: dockerfile:Dockerfile · Aug 20, 2026
Languages: c++, python
Source: github.language+pyproject.toml · Aug 20, 2026

Graph entities

vLLMcompany

README

Getting Started

Please use the following recommended versions to get started quickly:

Version	Release type	Doc
v0.23.0	Latest stable version	See QuickStart and Installation for more details

License

Apache License 2.0, as found in the LICENSE file.

For agents

This page has a .md twin and JSON over the API.

/tools/vllm-project-vllm-ascend.md GET /api/graphcanon/tools/vllm-project-vllm-ascend GET /api/graphcanon/graph?tool=vllm-project-vllm-ascend