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 benchmark serving cannot use Qwen tokenizer #443

Merged
merged 2 commits into from
Sep 26, 2023
Merged

fix benchmark serving cannot use Qwen tokenizer #443

merged 2 commits into from
Sep 26, 2023

Conversation

AllentDan
Copy link
Collaborator

@AllentDan AllentDan requested a review from lvhan028 September 20, 2023 07:40
@AllentDan AllentDan mentioned this pull request Sep 20, 2023
Closed
2 tasks
@lvhan028 lvhan028 requested a review from irexyc September 26, 2023 06:22
AllentDan
AllentDan commented Sep 26, 2023
View reviewed changes
benchmark/profile_restful_api.py
completions_token_lens = tokenizer.encode(completions)
prompts_token_lens = [len(tokenizer.encode(prompt)) for prompt in prompts]
completions_token_lens = [
len(tokenizer.encode(prompt)) for prompt in completions
Copy link
Collaborator Author

@AllentDan AllentDan Sep 26, 2023 •
edited
Loading

Choose a reason for hiding this comment

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

this is slower compared with self.sp_model.Encode.

@lvhan028 lvhan028 merged commit 97dcdff into InternLM:main Sep 26, 2023
1 check passed
@AllentDan AllentDan mentioned this pull request Sep 28, 2023
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@irexyc irexyc irexyc approved these changes

@lvhan028 lvhan028 lvhan028 approved these changes

Assignees
No one assigned
Labels
Bug:P1
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@AllentDan @lvhan028 @irexyc