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

bump version to v0.2.3 #1123

Merged
merged 1 commit into from
Feb 6, 2024
Merged

bump version to v0.2.3 #1123

merged 1 commit into from
Feb 6, 2024

Conversation

lvhan028
Copy link
Collaborator

@lvhan028 lvhan028 commented Feb 5, 2024

No description provided.

@zhyncs
Copy link
Contributor

zhyncs commented Feb 5, 2024

Hi @lvhan028 hold on please

After #1085, this doesn't work as before.

python3 -m lmdeploy serve api_server /workdir/workspace

traceback

  File "/workdir/lmdeploy/lmdeploy/serve/async_engine.py", line 111, in _build_turbomind
    raise ArgumentError('Please set model_name or backend_config.')
TypeError: __init__() missing 1 required positional argument: 'message'

I have to set model-name explicitly like this.

python3 -m lmdeploy serve api_server /workdir/workspace --model-name llama2

Is this an expected feature or a bug? If it’s a bug, may I fix it before releasing it?

@lvhan028
Copy link
Collaborator Author

lvhan028 commented Feb 5, 2024

@irexyc

@irexyc
Copy link
Collaborator

irexyc commented Feb 5, 2024

@zhyncs

I can't reproduce your error, are you using the latest main code?

According to your error, the error line is 111, but the code in main branch is at line 109

  File "/workdir/lmdeploy/lmdeploy/serve/async_engine.py", line 111, in _build_turbomind
    raise ArgumentError('Please set model_name or backend_config.')
TypeError: __init__() missing 1 required positional argument: 'message'

@zhyncs
Copy link
Contributor

zhyncs commented Feb 5, 2024

@zhyncs

I can't reproduce your error, are you using the latest main code?

According to your error, the error line is 111, but the code in main branch is at line 109

  File "/workdir/lmdeploy/lmdeploy/serve/async_engine.py", line 111, in _build_turbomind
    raise ArgumentError('Please set model_name or backend_config.')
TypeError: __init__() missing 1 required positional argument: 'message'

Yes, I use the latest main code.

@zhyncs
Copy link
Contributor

zhyncs commented Feb 5, 2024

@irexyc use the llama 2 13b chat workspace please

@irexyc
Copy link
Collaborator

irexyc commented Feb 5, 2024

Found the reason. It was because my workspace folder had a name like vicuna so the best_match_model function can match it to the right model. If the workspace had a name like worksapce, it would failed.

@zhyncs
Copy link
Contributor

zhyncs commented Feb 5, 2024

Since the _from_workspace handles the model_name

self.model_name = cfg.model_name

We don't need raise the exception like this
potential_names = best_match_model(model_path)
if potential_names is None:
raise ArgumentError('Please set model_name or backend_config.')

@zhyncs
Copy link
Contributor

zhyncs commented Feb 5, 2024

Found the reason

Fine, may I send the pr? It's up to you.

@zhyncs
Copy link
Contributor

zhyncs commented Feb 5, 2024

According to your error, the error line is 111, but the code in main branch is at line 109

I added pdb LOL. It's same.

@zhyncs
Copy link
Contributor

zhyncs commented Feb 5, 2024

Hi @irexyc May you help review this pr #1125? Thanks.

Copy link
Collaborator

@RunningLeon RunningLeon left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@RunningLeon RunningLeon merged commit 2831dc2 into main Feb 6, 2024
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

4 participants