Originally created by @dennisorlando on GitHub (Feb 2, 2025).
Hi, for the folks out there using open-webui with ollama, it would be nice to have some mechanism to view which model is currently eating up the VRAM and then give us the option of unloading them / auto unloading them after x seconds
Originally created by @dennisorlando on GitHub (Feb 2, 2025).
Hi, for the folks out there using open-webui with ollama, it would be nice to have some mechanism to view which model is currently eating up the VRAM and then give us the option of unloading them / auto unloading them after x seconds
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @dennisorlando on GitHub (Feb 2, 2025).
Hi, for the folks out there using open-webui with ollama, it would be nice to have some mechanism to view which model is currently eating up the VRAM and then give us the option of unloading them / auto unloading them after x seconds