github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2490] [Question] Do not offload to CPU RAM #47965

New Issue
Closed
opened 2026-04-28 06:12:29 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 06:12:29 -05:00
Owner
Copy Link

Originally created by @freQuensy23-coder on GitHub (Feb 14, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2490

By default, after some time of inactivity, ollama will automatically be offloaded from GPU memory, that caused some latency, especially to large models)

Originally created by @freQuensy23-coder on GitHub (Feb 14, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2490 By default, after some time of inactivity, ollama will automatically be offloaded from GPU memory, that caused some latency, especially to large models)
GiteaMirror commented 2026-04-28 06:12:31 -05:00
Author
Owner
Copy Link

@wrapss commented on GitHub (Feb 14, 2024):

look this PR

<!-- gh-comment-id:1943605740 --> @wrapss commented on GitHub (Feb 14, 2024): look this [PR](https://github.com/ollama/ollama/pull/2146)
GiteaMirror commented 2026-04-28 06:12:33 -05:00
Author
Owner
Copy Link

@hoyyeva commented on GitHub (Mar 11, 2024):

@freQuensy23-coder is this still an issue that you are experiencing? You should be able to set the keep_alive to -1 to prevent that. Let us know if you are still running into the same issue.

<!-- gh-comment-id:1989164841 --> @hoyyeva commented on GitHub (Mar 11, 2024): @freQuensy23-coder is this still an issue that you are experiencing? You should be able to set the `keep_alive` to `-1` to prevent that. Let us know if you are still running into the same issue.
GiteaMirror commented 2026-04-28 06:12:34 -05:00
Author
Owner
Copy Link

@Mayorc1978 commented on GitHub (Mar 16, 2024):

look this PR

How do you use the keepalive parameter when accessing models from code?
Using Ollama for Windows installer.

<!-- gh-comment-id:2002102226 --> @Mayorc1978 commented on GitHub (Mar 16, 2024): > look this [PR](https://github.com/ollama/ollama/pull/2146) How do you use the `keepalive` parameter when accessing models from code? Using **Ollama for Windows** installer.
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#47965
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?