Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[BUG] <title>离线部署问题汇总 #564

Open
2 tasks done
num-doc opened this issue Oct 30, 2024 · 1 comment
Open
2 tasks done

[BUG] <title>离线部署问题汇总 #564

num-doc opened this issue Oct 30, 2024 · 1 comment

Comments

@num-doc
Copy link

num-doc commented Oct 30, 2024

是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this?

  • 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答? | Is there an existing answer for this in FAQ?

  • 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

文档不完整 且存在问题
1.离线部署中需要打包5个镜像 实际需要打包6个才能运行
2.断网机器加载镜像后仍然需要下载第三方依赖 比如 pychda(用于获取显卡算力) 但是镜像中是没有包含这些依赖的。。。
3.运行run.sh 报错无报错日志 (最新报错error: bc 命令不存在,请使用 sudo apt update && sudo apt-get install bc 安装,再重新启动。 )

官方交流群 无人响应 没有相关人员回复技术问题。。。。

期望行为 | Expected Behavior

能否解决一下离线部署问题.....
另外群聊中能否安排人回复一下 莫不是群里的技术都是机器人?

运行环境 | Environment

- OS:UBUNTU22.04
- NVIDIA Driver:550.120
- CUDA:12.1
- Docker Compose: 2.29.6
- NVIDIA GPU Memory: 24G

QAnything日志 | QAnything logs

No response

复现方法 | Steps To Reproduce

参考离线部署文档
1.准备 安装驱动 cuda docker docker-compose nvidia-docker
2.拉镜像 一共6个 文档不全只拉了五个
3.git zip
4.解压运行

备注 | Anything else?

No response

@num-doc
Copy link
Author

num-doc commented Oct 30, 2024

离线运行 报错 算力无法识别的问题 原因是docker 里面没有打最新pycuda 的环境

找到 scripy/get_cuda_capability.py 文件 全部注释
只保留 cmp_ver=8.9 (4090 算力8.9 找到对应显卡算力)
原来的读取json 文件很方便。。。。。

@num-doc num-doc changed the title [BUG] <title>离线部署问题 bc 命令不存在 安装后仍然报错! [BUG] <title>离线部署问题汇总 Oct 30, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant