github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10802] Auto-update Toggle #69153

New Issue
Closed
opened 2026-05-04 17:17:51 -05:00 by GiteaMirror · 13 comments
GiteaMirror commented 2026-05-04 17:17:51 -05:00
Owner
Copy Link

Originally created by @novaexe on GitHub (May 21, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10802

in lue of the broken https://github.com/ollama/ollama/releases/tag/v0.7.0 release on vlm's please re-consider #6024 #4498 #3459

Originally created by @novaexe on GitHub (May 21, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10802 in lue of the broken https://github.com/ollama/ollama/releases/tag/v0.7.0 release on vlm's please re-consider #6024 #4498 #3459
GiteaMirror added the feature request label 2026-05-04 17:17:51 -05:00
GiteaMirror commented 2026-05-04 17:17:53 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 21, 2025):

Thanks for the issue @novaexe. May I ask what broke in 0.7.0 with VLMs? Will make sure we take a look at that

<!-- gh-comment-id:2898390942 --> @jmorganca commented on GitHub (May 21, 2025): Thanks for the issue @novaexe. May I ask what broke in 0.7.0 with VLMs? Will make sure we take a look at that
GiteaMirror commented 2026-05-04 17:17:54 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 21, 2025):

llama3.2-vision quality degraded (#10731). I haven't seen any problems with other VLMs.

<!-- gh-comment-id:2898398798 --> @rick-github commented on GitHub (May 21, 2025): llama3.2-vision quality degraded (#10731). I haven't seen any problems with other VLMs.
GiteaMirror commented 2026-05-04 17:17:54 -05:00
Author
Owner
Copy Link

@novaexe commented on GitHub (May 21, 2025):

@jmorganca see the most recent cpu issues pertaining to models with img processing capabilities, in my own testing it will softlock my entire system on 0.7 this issue does not exist in .6.8

<!-- gh-comment-id:2898404212 --> @novaexe commented on GitHub (May 21, 2025): @jmorganca see the most recent cpu issues pertaining to models with img processing capabilities, in my own testing it will softlock my entire system on 0.7 this issue does not exist in .6.8
GiteaMirror commented 2026-05-04 17:17:54 -05:00
Author
Owner
Copy Link

@novaexe commented on GitHub (May 21, 2025):

would assume all sept one are part of the same issue

Image

<!-- gh-comment-id:2898428159 --> @novaexe commented on GitHub (May 21, 2025): would assume all sept one are part of the same issue ![Image](https://github.com/user-attachments/assets/a9a251db-1f3c-44e5-94fe-ae665d0d688d)
GiteaMirror commented 2026-05-04 17:17:55 -05:00
Author
Owner
Copy Link

@novaexe commented on GitHub (May 21, 2025):

but either way mine is a feature request for pause/rollback functionality on windows specifically, cause now it will ping me for an update, take up 1gb on my system, and i assume double update once the issues is resolved

<!-- gh-comment-id:2898435582 --> @novaexe commented on GitHub (May 21, 2025): but either way mine is a feature request for pause/rollback functionality on windows specifically, cause now it will ping me for an update, take up 1gb on my system, and i assume double update once the issues is resolved
GiteaMirror commented 2026-05-04 17:17:56 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 21, 2025):

10801 is a VRAM size issue
10800 looks like a context buffer size isue
10799 is a grammar buffer issue
10798 is a VRAM size issue
10797 is a VRAM size issue

None of this will cause a system to softlock.

<!-- gh-comment-id:2898439955 --> @rick-github commented on GitHub (May 21, 2025): 10801 is a VRAM size issue 10800 looks like a context buffer size isue 10799 is a grammar buffer issue 10798 is a VRAM size issue 10797 is a VRAM size issue None of this will cause a system to softlock.
GiteaMirror commented 2026-05-04 17:17:56 -05:00
Author
Owner
Copy Link

@novaexe commented on GitHub (May 21, 2025):

@rick-github all i know is on 3 separate front-ends, chat works as far as i can tell, but the moment i upload an img of any size and ask gemma3, qwen, to describe it, it throws my cpu above what it's capable of doing, softlocking my system cause of cpu over utilization
and again this does not happen in .6.8

<!-- gh-comment-id:2898449882 --> @novaexe commented on GitHub (May 21, 2025): @rick-github all i know is on 3 separate front-ends, chat works as far as i can tell, but the moment i upload an img of any size and ask gemma3, qwen, to describe it, it throws my cpu above what it's capable of doing, softlocking my system cause of cpu over utilization and again this does not happen in .6.8
GiteaMirror commented 2026-05-04 17:17:57 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 21, 2025):

Server logs may aid in diagnosis.

The VRAM issue is being attended to with #10773, that's the only thing I can think of that would remotely cause any issues.

<!-- gh-comment-id:2898453392 --> @rick-github commented on GitHub (May 21, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may aid in diagnosis. The VRAM issue is being attended to with #10773, that's the only thing I can think of that would remotely cause any issues.
GiteaMirror commented 2026-05-04 17:17:57 -05:00
Author
Owner
Copy Link

@novaexe commented on GitHub (May 21, 2025):

hopefully that does fix the issue and im wrong about the cpu over utilization (hard to tell whats actually going on when ur rig is softlocked)

but my feature request still stands, many have requested it and it makes perfect sense to do so, as until that issue is resolved,

now it will ping me for an update, take up 1gb on my system, and i assume double update once the issues is resolved

<!-- gh-comment-id:2898477860 --> @novaexe commented on GitHub (May 21, 2025): hopefully that does fix the issue and im wrong about the cpu over utilization (hard to tell whats actually going on when ur rig is softlocked) but my feature request still stands, many have requested it and it makes perfect sense to do so, as until that issue is resolved, > now it will ping me for an update, take up 1gb on my system, and i assume double update once the issues is resolved
GiteaMirror commented 2026-05-04 17:17:57 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 21, 2025):

Sure. If you want your softlock issue investigated, open a new ticket and add logs.

<!-- gh-comment-id:2898480978 --> @rick-github commented on GitHub (May 21, 2025): Sure. If you want your softlock issue investigated, open a new ticket and add logs.
GiteaMirror commented 2026-05-04 17:17:58 -05:00
Author
Owner
Copy Link

@novaexe commented on GitHub (May 21, 2025):

will do if that pr doesnt fix the issue but i just spent the better part of 2 hrs figuring out there's no feasible way to prevent ollama to stop auto updating, hence my feature request xD

<!-- gh-comment-id:2898487359 --> @novaexe commented on GitHub (May 21, 2025): will do if that pr doesnt fix the issue but i just spent the better part of 2 hrs figuring out there's no feasible way to prevent ollama to stop auto updating, hence my feature request xD
GiteaMirror commented 2026-05-04 17:17:58 -05:00
Author
Owner
Copy Link

@YonTracks commented on GitHub (May 22, 2025):

this is very interesting (the bit about) the ping and 1gb. I have disabled the update for myself, but maybe now silently adding the memory, do you mean the notification adds the 1gb. anyway, for me in lifecycle/lifecycle.go I just commented out the updater check.

// StartBackgroundUpdaterChecker(ctx, t.UpdateAvailable)

but either way mine is a feature request for pause/rollback functionality on windows specifically, cause now it will ping me for an update, take up 1gb on my system, and i assume double update once the issues is resolved

<!-- gh-comment-id:2899854730 --> @YonTracks commented on GitHub (May 22, 2025): this is very interesting (the bit about) the ping and 1gb. I have disabled the update for myself, but maybe now silently adding the memory, do you mean the notification adds the 1gb. anyway, for me in lifecycle/lifecycle.go I just commented out the updater check. // StartBackgroundUpdaterChecker(ctx, t.UpdateAvailable) > but either way mine is a feature request for pause/rollback functionality on windows specifically, cause now it will ping me for an update, take up 1gb on my system, and i assume double update once the issues is resolved
GiteaMirror commented 2026-05-04 17:17:59 -05:00
Author
Owner
Copy Link

@YonTracks commented on GitHub (May 22, 2025):

ahh I see, it will download and have it ready. ok. cheers

<!-- gh-comment-id:2899859233 --> @YonTracks commented on GitHub (May 22, 2025): ahh I see, it will download and have it ready. ok. cheers
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 feature request
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#69153
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?