[GH-ISSUE #8784] Rerranking not using gpu #53920

Closed
opened 2026-05-05 15:34:19 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @fireblade2534 on GitHub (Jan 23, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/8784

Installation Method

Docker

Environment

  • Open WebUI Version: V0.5.6

  • Operating System: Ubuntu

Confirmation:

  • I have read and followed all the instructions provided in the README.md.
  • I am on the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below.

Expected Behavior:

Fast reranking performance

Actual Behavior:

It doesn't seem like reranking is run on the gpu even when it is available

Description

Bug Summary:
The reranking model doesn't seem to use the gpu resulting in bad performance

Reproduction Details

Steps to Reproduce:
Add a reranking model and use nvidia-smi to check gpu memory. Running RAG with and without the reranker does not change the ammount of gpu memory usage

Originally created by @fireblade2534 on GitHub (Jan 23, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/8784 ## Installation Method Docker ## Environment - **Open WebUI Version:** V0.5.6 - **Operating System:** Ubuntu **Confirmation:** - [ ] I have read and followed all the instructions provided in the README.md. - [ ] I am on the latest version of both Open WebUI and Ollama. - [ ] I have included the browser console logs. - [ ] I have included the Docker container logs. - [ ] I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below. ## Expected Behavior: Fast reranking performance ## Actual Behavior: It doesn't seem like reranking is run on the gpu even when it is available ## Description **Bug Summary:** The reranking model doesn't seem to use the gpu resulting in bad performance ## Reproduction Details **Steps to Reproduce:** Add a reranking model and use nvidia-smi to check gpu memory. Running RAG with and without the reranker does not change the ammount of gpu memory usage
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#53920