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

embedding模型指定gpu启动报错 #2707

Open
1 of 3 tasks
jingzl opened this issue Dec 26, 2024 · 1 comment
Open
1 of 3 tasks

embedding模型指定gpu启动报错 #2707

jingzl opened this issue Dec 26, 2024 · 1 comment
Labels
Milestone

Comments

@jingzl
Copy link

jingzl commented Dec 26, 2024

System Info / 系統信息

系统:ubuntu22.04
Driver Version: 535.129.03
CUDA 12.2

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

xinference, version 1.1.0

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

docker run -d
--name xinference
-v /data/xinference/data/.xinference:/root/.xinference
-v /data/xinference/data/.cache/huggingface:/root/.cache/huggingface
-v /data/xinference/data/.cache/modelscope:/root/.cache/modelscope
-v /data/xinference/log:/workspace/xinference/logs
-e XINFERENCE_HOME=/data/xinference
-e XINFERENCE_MODEL_SRC=modelscope
-e CUDA_DEVICE_ORDER=PCI_BUS_ID
-e PYTORCH_NVML_BASED_CUDA_CHECK=1
-e CUDA_VISIBLE_DEVICES=0,1,2,3
-p 3000:9997
--gpus all
--restart always
xprobe/xinference:latest
xinference-local -H 0.0.0.0 --log-level debug

Reproduction / 复现过程

image

Expected behavior / 期待表现

正常启动模型

@XprobeBot XprobeBot added the gpu label Dec 26, 2024
@XprobeBot XprobeBot added this to the v1.x milestone Dec 26, 2024
@qinxuye
Copy link
Contributor

qinxuye commented Dec 26, 2024

Xinference 镜像要求 cuda 12.4 了,12.2 可能会有问题。

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

3 participants