github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-08-27 06:46:30 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #8160] v0.5.2 Token Generation Slower Than v0.4.8 #15023

New Issue
Closed
opened 2026-04-19 21:18:42 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-19 21:18:42 -05:00
Owner
Copy Link
Copy Source

Originally created by @yanghan-cyber on GitHub (Dec 28, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/8160

Performance Regression in Token Generation Speed (v0.5.2 vs v0.4.8)

Environment Details

  • Version: v0.5.2
  • Deployment Method: Docker
  • Backend: Open-WebUI
  • API Management: Self-hosted OneAPI for OpenAI API

Issue Description

I've noticed a significant performance degradation in token generation speed when comparing version v0.5.2 to v0.4.8.

Steps to Reproduce

  1. Deploy Open-WebUI using Docker
  2. Use OneAPI to manage OpenAI API
  3. Compare token generation speed between v0.4.8 and v0.5.2

Observed Behavior

  • In v0.4.8: Token generation was faster and more responsive
  • In v0.5.2: Token generation speed has noticeably decreased

Expected Behavior

Token generation speed should remain consistent or improve between versions.

Additional Information

  • Can provide more detailed performance metrics if needed
  • Willing to assist in debugging or providing more information

Suggested Next Steps

  • Investigate potential performance regressions
  • Review changes between v0.4.8 and v0.5.2 that might impact token generation speed
Originally created by @yanghan-cyber on GitHub (Dec 28, 2024). Original GitHub issue: https://github.com/open-webui/open-webui/issues/8160 ## Performance Regression in Token Generation Speed (v0.5.2 vs v0.4.8) ### Environment Details - **Version**: v0.5.2 - **Deployment Method**: Docker - **Backend**: Open-WebUI - **API Management**: Self-hosted OneAPI for OpenAI API ### Issue Description I've noticed a significant performance degradation in token generation speed when comparing version v0.5.2 to v0.4.8. ### Steps to Reproduce 1. Deploy Open-WebUI using Docker 2. Use OneAPI to manage OpenAI API 3. Compare token generation speed between v0.4.8 and v0.5.2 ### Observed Behavior - In v0.4.8: Token generation was faster and more responsive - In v0.5.2: Token generation speed has noticeably decreased ### Expected Behavior Token generation speed should remain consistent or improve between versions. ### Additional Information - Can provide more detailed performance metrics if needed - Willing to assist in debugging or providing more information ### Suggested Next Steps - Investigate potential performance regressions - Review changes between v0.4.8 and v0.5.2 that might impact token generation speed
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No labels
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#15023