github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 21:25:46 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #6488] Ollama serve crashes with llama3.1:70b #29842

New Issue
Closed
opened 2026-04-22 09:06:39 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-22 09:06:39 -05:00
Owner
Copy Link

Originally created by @remco-pc on GitHub (Aug 24, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6488

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

i am running this command:

ollama run llama3.1:70b "can you give me the route to account: $(cat '/tmp/r3m/io/3d651238-75bf-4d4d-a1e1-7c902a83450c/0/Node/List/System.Route.7995d5f2c60a87c4b09a3515ef58f1b75af24058.json')"

and at the end of the response (mid way) it just crashes.

The model runs on the cpu

OS

Linux
Debian 12.6

GPU

Other

CPU

Intel

Ollama version

ollama version is 0.3.6

Originally created by @remco-pc on GitHub (Aug 24, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6488 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? i am running this command: ollama run llama3.1:70b "can you give me the route to account: $(cat '/tmp/r3m/io/3d651238-75bf-4d4d-a1e1-7c902a83450c/0/Node/List/System.Route.7995d5f2c60a87c4b09a3515ef58f1b75af24058.json')" and at the end of the response (mid way) it just crashes. The model runs on the cpu ### OS Linux Debian 12.6 ### GPU Other ### CPU Intel ### Ollama version ollama version is 0.3.6
GiteaMirror added the bugneeds more info labels 2026-04-22 09:06:39 -05:00
GiteaMirror commented 2026-04-22 09:06:40 -05:00
Author
Owner
Copy Link

@remco-pc commented on GitHub (Aug 24, 2024):

i might know what the error is:
OLLAMA_KEEP_ALIVE (default "5m") is too short for my model, it is still generating at that point (it might take more then 5 minutes on my computer to generate a response ?)

<!-- gh-comment-id:2308177042 --> @remco-pc commented on GitHub (Aug 24, 2024): i might know what the error is: OLLAMA_KEEP_ALIVE (default "5m") is too short for my model, it is still generating at that point (it might take more then 5 minutes on my computer to generate a response ?)
GiteaMirror commented 2026-04-22 09:06:41 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 24, 2024):

The keep-alive timer doesn't start until the generation is finished. If you could provide server logs it would help with debugging.

<!-- gh-comment-id:2308354670 --> @rick-github commented on GitHub (Aug 24, 2024): The keep-alive timer doesn't start until the generation is finished. If you could provide [server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) it would help with debugging.
GiteaMirror commented 2026-04-22 09:06:41 -05:00
Author
Owner
Copy Link

@remco-pc commented on GitHub (Aug 25, 2024):

@rick-github i don't have a server log yet (no entries)

<!-- gh-comment-id:2308628338 --> @remco-pc commented on GitHub (Aug 25, 2024): @rick-github i don't have a server log yet (no entries)
GiteaMirror commented 2026-04-22 09:06:42 -05:00
Author
Owner
Copy Link

@viba1 commented on GitHub (Aug 30, 2024):

  1. The model runs on the cpu => no gpu?
  2. Ollama serve crashes => just Ollama crashes or the whole server (host machine)?
  3. Is Ollama directly installed on the host or on a VM or in a docker container?
<!-- gh-comment-id:2322332680 --> @viba1 commented on GitHub (Aug 30, 2024): 1. The model runs on the cpu => no gpu? 2. Ollama serve crashes => just Ollama crashes or the whole server (host machine)? 3. Is Ollama directly installed on the host or on a VM or in a docker container?
GiteaMirror commented 2026-04-22 09:06:42 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Sep 1, 2024):

@remco-pc any update w/ the server logs?

<!-- gh-comment-id:2323538796 --> @pdevine commented on GitHub (Sep 1, 2024): @remco-pc any update w/ the server logs?
GiteaMirror commented 2026-04-22 09:06:43 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Sep 5, 2024):

@remco-pc can you clarify "and at the end of the response (mid way) it just crashes."

Do you get any output? If you get any output, there has to be some server log to go along with loading the model. I'm assuming the server crashed, so the crash information should be in the server log.

<!-- gh-comment-id:2332861743 --> @dhiltgen commented on GitHub (Sep 5, 2024): @remco-pc can you clarify "and at the end of the response (mid way) it just crashes." Do you get any output? If you get any output, there has to be some server log to go along with loading the model. I'm assuming the server crashed, so the crash information should be in the server log.
GiteaMirror commented 2026-04-22 09:06:44 -05:00
Author
Owner
Copy Link

@remco-pc commented on GitHub (Sep 8, 2024):

i am currently not having issues, if i have issues i will create a new ticket

<!-- gh-comment-id:2336675261 --> @remco-pc commented on GitHub (Sep 8, 2024): i am currently not having issues, if i have issues i will create a new ticket
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 bug needs more info
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#29842
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?