mirror of
https://github.com/open-webui/open-webui.git
synced 2026-11-09 10:50:35 -06:00
[GH-ISSUE #17104] feat: Show inference statistics, such as tokens-per-second speed, for openai compatible inference engines #33695
Reference in New Issue
Block a user
Originally created by @drp4rad0x on GitHub (Sep 1, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/17104
Check Existing Issues
Problem Description
I created an issue as a bug, but the maintainer said it is intended functionality, so I think it is not a bug but a feature request. Open WebUI doesn't show inference statistics, such as tokens-per-second speed, for inference engines other than Ollama
Desired Solution you'd like
I want to see all prompt_token/s speed in webui
Alternatives Considered
No response
Additional Context
No response
@tjbck commented on GitHub (Sep 1, 2025):
The model inference engines themselves need to forward the stats, we already support usage field in the response.