OpenBMB / OpenBMB/MiniCPM

[Feature Request] MiniCPM5-2B 在 RK3576 内置 NPU 上的支持情况与部署方式

Open
#373 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature
Dominant language
Jupyter Notebook
Stars
11.1k
Forks
763
Avg merge
6h 3m
Merged PRs (30d)
5

Description

Feature request / 功能建议

感谢团队开源 MiniCPM5-2B!

我希望在 RK3576 设备上使用内置 NPU 运行 MiniCPM5-2B,不外接 RK1820/RK1828 等协处理器。看到发布信息提到“瑞芯微平台 Day0 适配”,但暂时没有找到针对这一配置的部署说明,想请教:

  1. 本次 Day0 适配是否包含单 RK3576 的内置 NPU,还是主要针对搭配 RK1820/RK1828 的双芯方案?
  2. 如果已支持 RK3576,能否提供所需的 RKLLM SDK 版本、模型转换步骤或预转换的 .rkllm 模型下载地址?
  3. 如果暂未支持,是否有后续适配计划,或建议尝试的部署路径?

谢谢!

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files, tests, or entry points are mentioned. Start by checking the project's MiniCPM5 release information and any RKLLM deployment documentation for RK3576, then confirm whether the built-in NPU is supported and what SDK, conversion steps, or model artifact are required. Done means the support status and a reproducible deployment path are documented.

Written by the indexing model from the issue text.

Assessment

Domain
ai-infra-agents, embedded-iot, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.