github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1951] Ollama GPU Process does not automatically terminate after inactivity #47637

New Issue
Closed
opened 2026-04-28 04:39:24 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 04:39:24 -05:00
Owner
Copy Link

Originally created by @chereszabor on GitHub (Jan 12, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/1951

Originally assigned to: @dhiltgen on GitHub.

Noticed with recent releases the ollama process does not get automatically terminated after a period of inactivity, idling the GPU process and keeping the last used model in VRAM. This also increases the time required to load a new model into VRAM and increases 'standby' power usage of the GPU.

I am deploying ollama via Docker and tested with the latest version v0.1.20.

Originally created by @chereszabor on GitHub (Jan 12, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/1951 Originally assigned to: @dhiltgen on GitHub. Noticed with recent releases the ollama process does not get automatically terminated after a period of inactivity, idling the GPU process and keeping the last used model in VRAM. This also increases the time required to load a new model into VRAM and increases 'standby' power usage of the GPU. I am deploying ollama via Docker and tested with the latest version v0.1.20.
GiteaMirror commented 2026-04-28 04:39:26 -05:00
Author
Owner
Copy Link

@newjcj commented on GitHub (Jan 13, 2024):

me to!!!

<!-- gh-comment-id:1890327212 --> @newjcj commented on GitHub (Jan 13, 2024): me to!!!
GiteaMirror commented 2026-04-28 04:39:27 -05:00
Author
Owner
Copy Link

@cassidea commented on GitHub (Jan 17, 2024):

Same here. Model gets unloaded after some time but still ~120MB on the GPU preventing to switch into lower power states.

<!-- gh-comment-id:1895892869 --> @cassidea commented on GitHub (Jan 17, 2024): Same here. Model gets unloaded after some time but still ~120MB on the GPU preventing to switch into lower power states.
GiteaMirror commented 2026-04-28 04:39:27 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jan 18, 2024):

Closing as dup of #1848

<!-- gh-comment-id:1898867155 --> @dhiltgen commented on GitHub (Jan 18, 2024): Closing as dup of #1848
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#47637
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?