[GH-ISSUE #5581] Force ollama to use GPU #49999

Open
opened 2026-04-28 13:44:45 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @wirmius on GitHub (Jul 9, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5581

Me and, seemingly, a few people using this repo have been encountering a problem of the models being loaded into the CPU memory after inactivity/sleep mode/etc. Would there be a possibility to have a flag that would cause the ollama to fail if it cannot load the model onto the GPU and try again?

Originally created by @wirmius on GitHub (Jul 9, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5581 Me and, seemingly, a few people using this repo have been encountering a problem of the models being loaded into the CPU memory after inactivity/sleep mode/etc. Would there be a possibility to have a flag that would cause the ollama to fail if it cannot load the model onto the GPU and try again?
GiteaMirror added the feature request label 2026-04-28 13:44:45 -05:00
Author
Owner

@owenzhao commented on GitHub (Jul 13, 2024):

Maybe during the time your GPU driver had been updated. I had file a bug the after updating the Nvidia GPU driver, Ollama stopped using GPU acceleration until you restart Ollama service or your computer.

<!-- gh-comment-id:2226582472 --> @owenzhao commented on GitHub (Jul 13, 2024): Maybe during the time your GPU driver had been updated. I had file a bug the after updating the Nvidia GPU driver, Ollama stopped using GPU acceleration until you restart Ollama service or your computer.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#49999