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.

Sign up for GitHub

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

Jump to bottom

Embedding model is reloaded cyclic when run on CPU #2599

Open

1 of 3 tasks

liunux4odoo opened this issue Nov 28, 2024 · 0 comments

Open

1 of 3 tasks

Embedding model is reloaded cyclic when run on CPU #2599

liunux4odoo opened this issue Nov 28, 2024 · 0 comments

Labels

gpu

Milestone

Contributor

liunux4odoo commented Nov 28, 2024

System Info / 系統信息

system: win10
python: 3.10
transformers: 4.46.2

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

0.16.3 & 1.0.0

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

xinference-local.exe

Reproduction / 复现过程

start xinference-local.exe
launch bge-large-zh-v1.5 model on CPU in webui
do embedding request

The console logs model reload information repeated.
There is no problem if set device to GPU.

Expected behavior / 期待表现

serve embedding model normally on CPU device

The text was updated successfully, but these errors were encountered:

XprobeBot added the gpu label

XprobeBot added this to the v1.x milestone

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment