Skip to main content

vLLM Ascend backend plugin

Project description

vllm-ascend

vLLM Ascend Plugin

| About Ascend | Documentation | #sig-ascend | Users Forum | Weekly Meeting |

English | 中文


Latest News 🔥


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 in the [RFC]: Hardware pluggable, providing a hardware-pluggable interface that decouples the integration of the Ascend NPU with vLLM.

By using vLLM Ascend plugin, popular open-source models, including Transformer-like, Mixture-of-Expert, Embedding, Multi-modal LLMs can run seamlessly on the Ascend NPU.

Prerequisites

  • Hardware: Atlas 800I A2 Inference series, Atlas A2 Training series
  • OS: Linux
  • Software:
    • Python >= 3.9
    • CANN >= 8.0.0
    • PyTorch >= 2.5.1, torch-npu >= 2.5.1.dev20250320
    • vLLM (the same version as vllm-ascend)

Getting Started

Please refer to QuickStart and Installation for more details.

Contributing

See CONTRIBUTING for more details, which is a step-by-step guide to help you set up development environment, build and test.

We welcome and value any contributions and collaborations:

Branch

vllm-ascend has main branch and dev branch.

  • main: main branch,corresponds to the vLLM main branch, and is continuously monitored for quality through Ascend CI.
  • vX.Y.Z-dev: development branch, created with part of new releases of vLLM. For example, v0.7.3-dev is the dev branch for vLLM v0.7.3 version.

Below is maintained branches:

Branch Status Note
main Maintained CI commitment for vLLM main branch and vLLM 0.8.x branch
v0.7.1-dev Unmaintained Only doc fixed is allowed
v0.7.3-dev Maintained CI commitment for vLLM 0.7.3 version

Please refer to Versioning policy for more details.

Weekly Meeting

License

Apache License 2.0, as found in the LICENSE file.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vllm_ascend-0.8.4rc1.tar.gz (473.8 kB view details)

Uploaded Source

File details

Details for the file vllm_ascend-0.8.4rc1.tar.gz.

File metadata

  • Download URL: vllm_ascend-0.8.4rc1.tar.gz
  • Upload date:
  • Size: 473.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.9.6

File hashes

Hashes for vllm_ascend-0.8.4rc1.tar.gz
Algorithm Hash digest
SHA256 39a43a8016a9dc42e93c772dd60fd36f53a46facd941c3865c3940335c65ba35
MD5 de29441bf73c3891f71a15c872745d8f
BLAKE2b-256 3c94c79445f3ba0df6d8718417720ee10f4c9470ff831790efedc294316e6866

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page