• Recent
    • Docs
    • Github
    • 百度网盘
    • Onedrive
    • Official
    • Shop
    • Register
    • Login

    4b会支持rkllm版本么?

    Scheduled Pinned Locked Moved Pi 4B
    11 Posts 4 Posters 2.3k Views
    Loading More Posts
    • Oldest to Newest
    • Newest to Oldest
    • Most Votes
    Reply
    • Reply as topic
    Log in to reply
    This topic has been deleted. Only users with topic management privileges can see it.
    • G
      george @airobot机器人开发
      last edited by

      Description

      RKLLM software stack can help users to quickly deploy AI models to Rockchip chips. The overall framework is as follows:
      framework.jpg

      In order to use RKNPU, users need to first run the RKLLM-Toolkit tool on the computer, convert the trained model into an RKLLM format model, and then inference on the development board using the RKLLM C API.

      • RKLLM-Toolkit is a software development kit for users to perform model conversionand quantization on PC.

      • RKLLM Runtime provides C/C++ programming interfaces for Rockchip NPU platform to help users deploy RKLLM models and accelerate the implementation of LLM applications.

      • RKNPU kernel driver is responsible for interacting with NPU hardware. It has been open source and can be found in the Rockchip kernel code.

      Support Platform

      • RK3588 Series
      • RK3576 Series

      Download

      • You can also download all packages, docker image, examples, docs and platform-tools from RKLLM_SDK, fetch code: rkllm

      RKNN Toolkit2

      If you want to deploy additional AI model, we have introduced a new SDK called RKNN-Toolkit2. For details, please refer to:

      https://github.com/airockchip/rknn-toolkit2

      Notes

      Due to recent updates to the Phi2 model, the current version of the RKLLM SDK does not yet support these changes.
      Please ensure to download a version of the Phi2 model that is supported.

      CHANGELOG

      v1.0.0-beta

      • Supports the conversion and deployment of LLM models on RK3588/RK3576 platforms
      • Compatible with Hugging Face model architectures
      • Currently supports the models LLaMA, Qwen, Qwen2, and Phi-2
      • Supports quantization with w8a8 and w4a16 precision
      1 Reply Last reply Reply Quote 0
      • G
        george @airobot机器人开发
        last edited by

        @airobot机器人开发
        目前还是beta版本,等后续的release版本再考虑移植。如果有兴趣可以自己尝试移植,里边最主要的步骤是X86上面的模型转换过程。需要更详细资料可以邮件索取:george@cool-pi.com

        A S 2 Replies Last reply Reply Quote 0
        • A
          airobot机器人开发 @george
          last edited by

          @george 感谢

          1 Reply Last reply Reply Quote 0
          • S
            shengxia
            last edited by

            我自己是了一下qwen1.8b,是没问题的,但是换了4b会提示要升级npu驱动,

            然后我看到官方的仓库里有放出npu driver,就是不知道如何可以在板子上,直接编译,安装的方法

            A 1 Reply Last reply Reply Quote 0
            • S
              shengxia @george
              last edited by

              @george 这个huggingface上有兄弟上传了,我下载用了没问题

              1 Reply Last reply Reply Quote 0
              • A
                airobot机器人开发 @shengxia
                last edited by

                @shengxia 我试了不行,请问你用的哪个版本的固件?我试了加载没问题,但是实际运行就是乱输出,有时候是乱码,有时候就是乱输出一通。

                1 Reply Last reply Reply Quote 0
                • A
                  airobot机器人开发
                  last edited by

                  原来我自己转换的模型有问题,虽然用工具转换成功了,但是运行起来后都是乱码。不知道是否和转换时参数设置有关系

                  G 1 Reply Last reply Reply Quote 0
                  • G
                    george @airobot机器人开发
                    last edited by

                    @airobot机器人开发
                    你手上有完整的SDK吗,我邮件发一份给你,里边有比较详细的文档。

                    A 1 Reply Last reply Reply Quote 0
                    • A
                      airobot机器人开发 @george
                      last edited by

                      @george 有的,感谢。

                      1 Reply Last reply Reply Quote 0
                      • L
                        lunaberry
                        last edited by

                        请问可以也发我一份资料吗? 下载链接提供的模型,输出也有乱码问题。 我又尝试了下自己转换,但是rknn-llm安装whl也有问题,提示utf8编码无法解码文件。

                        1 Reply Last reply Reply Quote 0
                        • 1 / 1
                        • First post
                          Last post