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

llmdeploy 使用openai形式提示词请求报错[Bug] #1939

Closed

2 tasks done

hitzhu opened this issue Jul 6, 2024 · 3 comments

Closed

2 tasks done

llmdeploy 使用openai形式提示词请求报错[Bug] #1939

hitzhu opened this issue Jul 6, 2024 · 3 comments

hitzhu commented Jul 6, 2024

Checklist

1. I have searched related issues but cannot get the expected help.
2. The bug has not been fixed in the latest version.

Describe the bug

使用llmdeploy部署internvl ，并使用官方openai 形式的提示词demo请求,后端报错

Reproduction

rt

Environment

rt

Error traceback

No response

Collaborator

lvhan028 commented Jul 7, 2024

The internvl2 feature has been implemented in the latest main branch, but hasn't been released yet.
It is going to be released in v0.5.1 next week.

Collaborator

zhyncs commented Jul 7, 2024

@hitzhu You can install the latest whl from https://github.com/zhyncs/lmdeploy-build/releases/tag/ab5b7ce

hitzhu closed this as completed

Author

hitzhu commented Jul 9, 2024

已解决，根据commit记录改源码就可以

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