Skip to content

Conversation

@allozaur
Copy link
Collaborator

Close #16179

Added a setting to display generation statistics for each assistant message — tokens/s, amount of tokens in a message and generation time.

New Setting in the General section

Zrzut ekranu 2025-10-31 o 19 49 20

Statistics at the bottom of the assistant message

Zrzut ekranu 2025-10-31 o 19 33 46

@allozaur allozaur requested a review from ggerganov October 31, 2025 18:52
Copy link
Member

@ggerganov ggerganov left a comment

Choose a reason for hiding this comment

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

Great. Btw, we could also show the stats for the prompt, not just for the generated tokens. This ok for now - we can expand this information in the future.

@allozaur
Copy link
Collaborator Author

Great. Btw, we could also show the stats for the prompt, not just for the generated tokens. This ok for now - we can expand this information in the future.

@ggerganov would u be so kind and create an issue with just a basic breakdown of what you would like to see there?

@ggerganov
Copy link
Member

Here is the issue: #16902

@allozaur allozaur merged commit d8b860a into ggml-org:master Nov 1, 2025
14 checks passed
@allozaur allozaur deleted the 16179-stats-per-message branch November 1, 2025 14:36
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Misc. bug: Missing processing stats in the new SvelteKit WebUI

2 participants