Sign inSign up

baibgj/distroless-hello

By baibgj

Updated over 1 year ago

Image
0

343

baibgj/distroless-hello repository overview

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:

BranchStatusNote
mainMaintainedCI commitment for vLLM main branch
v0.7.1-devUnmaintainedOnly doc fixed is allowed
v0.7.3-devMaintainedCI 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. test

Tag summary

Content type

Image

Digest

sha256:6027871a0

Size

20.1 MB

Last updated

over 1 year ago

docker pull baibgj/distroless-hello