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 #3060] Ollama Server is unavailable after some time #48395

New Issue
Closed
opened 2026-04-28 08:04:03 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 08:04:03 -05:00
Owner
Copy Link

Originally created by @vrubzov1957 on GitHub (Mar 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3060

Sometimes after a certain amount of time working with the same AI model (after about an hour) the Ollama server becomes unavailable.

I have to start it via "ollama run MODEL" - server starts in the background, but closes again after a while.
Very inconvenient when we use a different frontend (like Ollama Web-UI) - we have to connect to the PC manually, and do the Ollama server startup again

LOG
server_ollama.log

In this logs the server became unavailable, then manually started, then became unavailable again. Periods 1-2 hours

OS: Windows

Originally created by @vrubzov1957 on GitHub (Mar 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3060 Sometimes after a certain amount of time working with the same AI model (after about an hour) the Ollama server becomes unavailable. I have to start it via "ollama run MODEL" - server starts in the background, but closes again after a while. Very inconvenient when we use a different frontend (like Ollama Web-UI) - we have to connect to the PC manually, and do the Ollama server startup again LOG [server_ollama.log](https://github.com/ollama/ollama/files/14562402/server_ollama.log) In this logs the server became unavailable, then manually started, then became unavailable again. Periods 1-2 hours OS: Windows
GiteaMirror commented 2026-04-28 08:04:06 -05:00
Author
Owner
Copy Link

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

Sorry about this. This seems to be an out of memory error with CUDA, I'll merge this with https://github.com/ollama/ollama/issues/1952

<!-- gh-comment-id:1989128818 --> @jmorganca commented on GitHub (Mar 11, 2024): Sorry about this. This seems to be an out of memory error with CUDA, I'll merge this with https://github.com/ollama/ollama/issues/1952
GiteaMirror commented 2026-04-28 08:04:07 -05:00
Author
Owner
Copy Link

@vrubzov1957 commented on GitHub (Mar 11, 2024):

@jmorganca ok.
Also I did note in #1952 - because may be different root cause of it. May be memory leaking. Because with selected model it works perfect, VRAM for model is enough. And after 20-30 newly-topic promts requests - Ollama server goes offline.

<!-- gh-comment-id:1989239559 --> @vrubzov1957 commented on GitHub (Mar 11, 2024): @jmorganca ok. Also I did note in #1952 - because may be different root cause of it. May be memory leaking. Because with selected model it works perfect, VRAM for model is enough. And after 20-30 newly-topic promts requests - Ollama server goes offline.
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#48395
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?