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

使用embbeding模型时,选择的是gpu,但实际没有用到gpu,仍然使用的cpu #2592

Closed
1 of 3 tasks
leon528 opened this issue Nov 27, 2024 · 1 comment
Closed
1 of 3 tasks
Labels
Milestone

Comments

@leon528
Copy link

leon528 commented Nov 27, 2024

System Info / 系統信息

ubuntu 22,CUDA Version: 12.5

Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece?

  • docker / docker
  • pip install / 通过 pip install 安装
  • installation from source / 从源码安装

Version info / 版本信息

v0.16.3

The command used to start Xinference / 用以启动 xinference 的命令

docker run -d --restart=always --name=xinference
-v /opt/xinference_gpu:/opt/xinference -e XINFERENCE_HOME=/opt/xinference -e XINFERENCE_MODEL_SRC=modelscope
-p 9998:9997 --gpus all xprobe/xinference:latest xinference-local -H 0.0.0.0 --log-level debug

Reproduction / 复现过程

1、在 lauch model 界面选择 embbeding 模型,device 选择 gpu,启动成功。
2、在 running model 界面能看到该 embbeding 模型运行成功。
3、在服务器上 运行 nvidia-smi ,显示 gpu 没有使用。
4、推理时,在服务器运行 top 命令,显示 cpu 使用率很高。

Expected behavior / 期待表现

使用gpu运行embbeding模型

@XprobeBot XprobeBot added the gpu label Nov 27, 2024
@XprobeBot XprobeBot added this to the v1.x milestone Nov 27, 2024
@leon528 leon528 closed this as completed Nov 27, 2024
@leon528
Copy link
Author

leon528 commented Nov 27, 2024

换成 v1.0.0 之后,问题解决。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants