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

compare-llama-bench.py: add missing basicConfig #7138

Merged
merged 3 commits into from
May 8, 2024

Conversation

mofosyne
Copy link
Collaborator

@mofosyne mofosyne commented May 8, 2024

Source Issue: #6511

@csaben

This has broken compare-llama-bench.py.

I believe it's due to missing this line logging.basicConfig(level=logging.DEBUG if known_args.verbose else logging.INFO). See if this fixes the issue for you.

@ggerganov ggerganov requested a review from slaren May 8, 2024 06:39
Copy link
Collaborator

@JohannesGaessler JohannesGaessler left a comment

Choose a reason for hiding this comment

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

The logging still messes up the table formatting:

INFO:compare-llama-bench:| GPU      | Model         | Test   |   t/s 60325fa5 |   t/s b49f134f |   Speedup |
|:---------|:--------------|:-------|---------------:|---------------:|----------:|
| RTX 3090 | llama 7B Q4_0 | pp4096 |         125.14 |         119.56 |      0.96 |

Also please re-add the line-breaks between error messages and print_help().

@JohannesGaessler
Copy link
Collaborator

More generally, unless I'm missing something the --verbose flag doesn't actually do anything. So my suggestion would be to just use regular prints for the table which would then also fix the need for the flag in the first place.

@mofosyne
Copy link
Collaborator Author

mofosyne commented May 8, 2024

Okay added both suggestions. Regarding the --verbose flag, it shall be kept to give future developers an option of using log_debug() without worrying about the output getting too polluted with debug messages.

@mofosyne mofosyne self-assigned this May 8, 2024
@JohannesGaessler JohannesGaessler merged commit acdce3c into ggerganov:master May 8, 2024
21 checks passed
@mofosyne mofosyne deleted the fix-compare-llama-bench branch May 8, 2024 10:50
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.

2 participants