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

xinference v1.0.0及以下版本需要升级transformer 4.45或以上,才可以正常启动qwen2-VL-instruct 模型 #2573

Open
1 of 3 tasks
cnrbi1 opened this issue Nov 23, 2024 · 1 comment
Labels
Milestone

Comments

@cnrbi1
Copy link

cnrbi1 commented Nov 23, 2024

System Info / 系統信息

容器镜像中的transformers版本是4.44.2

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 v1.0.0、xinference v0.16.3

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

docker run --name xinference -d -p 9997:9997 --restart always -e XINFERENCE_HOME=/data -e XINFERENCE_MODEL_SRC=modelscope -v xinference_data:/data --gpus all xprobe/xinference:latest xinference-local -H 0.0.0.0

Reproduction / 复现过程

启动中报错:Server error. 500 - [address=0.0.0.0.44775, pid=952] cannot import name 'Qwen2VLForconditionalGeneration'
from "transformers' (/usr/local/lib/python3.10/distpackages/transformers/ init .py)

Expected behavior / 期待表现

xinference v1.0.0及以下版本需要升级transformer 4.45或以上,才可以正常启动qwen2-VL-instruct 模型。建议容器对镜像中的transformer版本升级到4.45以上,当前是4.46可正常运行

@XprobeBot XprobeBot added the gpu label Nov 23, 2024
@XprobeBot XprobeBot added this to the v0.16 milestone Nov 23, 2024
@qinxuye
Copy link
Contributor

qinxuye commented Nov 23, 2024

欢迎提 PR 修改:

@XprobeBot XprobeBot modified the milestones: v0.16, v1.x Nov 25, 2024
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