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.

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

Fix concatenate issue in profile serving #1282

Merged
merged 1 commit into from
Mar 14, 2024
Merged

Fix concatenate issue in profile serving #1282

merged 1 commit into from
Mar 14, 2024

Conversation

ispobock
Copy link
Contributor

Motivation

  1. If the postprocessing grpc call failed, the text variable will be access but not declared.

    lmdeploy/lmdeploy/serve/turbomind/chatbot.py

    Line 683 in e7b2833

    session.response += text
  2. If num_prompts < concurrency, the np.concatenate() will face issue because the array dimension in stats is different.

Modification

  1. Add initialization for text variable
  2. Filter empty stats_ array.

@lvhan028 lvhan028 requested a review from AllentDan March 13, 2024 09:30
AllentDan
AllentDan approved these changes Mar 14, 2024
View reviewed changes
Copy link
Collaborator

@AllentDan AllentDan left a comment

Choose a reason for hiding this comment

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

LGTM

@lvhan028 lvhan028 merged commit 0c631a7 into InternLM:main Mar 14, 2024
4 of 5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@lvhan028 lvhan028 lvhan028 approved these changes

@AllentDan AllentDan AllentDan approved these changes

Assignees
No one assigned
Labels
Bug:P2
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
3 participants
@ispobock @lvhan028 @AllentDan