github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 13:47:08 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #1372] Runner stops, error 0 #723

New Issue
Closed
opened 2026-04-12 10:23:21 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-12 10:23:21 -05:00
Owner
Copy Link

Originally created by @FamousL on GitHub (Dec 4, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1372

Ollama version 0.1.13
Fedora 39 - 6.5.11-300.fc39.x86_64
Ollama runs until I attempt to run a model, then I get this error. This occurs between two different machines, ollama version 0.1.12 works fine.

[247685.858191] traps: ollama-runner[16373] trap invalid opcode ip:5012fc sp:7ffd01fd2090 error:0 in ollama-runner[408000+163000]
[247896.830423] traps: ollama-runner[49738] trap invalid opcode ip:5012fc sp:7ffd84c37730 error:0 in ollama-runner[408000+163000]
[248390.938706] traps: ollama-runner[102749] trap invalid opcode ip:5012fc sp:7ffdfca4d610 error:0 in ollama-runner[408000+163000]
[251176.665072] traps: ollama-runner[482136] trap invalid opcode ip:5651efba4730 sp:7ffd1c8c38f0 error:0 in ollama-runner[5651efaa4000+16a000]
[251309.955591] traps: ollama-runner[502961] trap invalid opcode ip:561f0918e730 sp:7ffe4b64d630 error:0 in ollama-runner[561f0908e000+16a000]
[251451.113782] traps: ollama-runner[524361] trap invalid opcode ip:560c87498730 sp:7ffcb6fe1b90 error:0 in ollama-runner[560c87398000+16a000]
[251620.818410] traps: ollama-runner[548566] trap invalid opcode ip:56190fc6b730 sp:7ffeb7c3bff0 error:0 in ollama-runner[56190fb6b000+16a000]
[271956.792336] traps: ollama-runner[3942233] trap invalid opcode ip:5012fc sp:7ffe72221110 error:0 in ollama-runner[408000+163000]
[271976.986598] traps: ollama-runner[3942286] trap invalid opcode ip:5012fc sp:7ffc06e5b210 error:0 in ollama-runner[408000+163000]
[271992.184077] traps: ollama-runner[3942454] trap invalid opcode ip:5012fc sp:7ffcafcd35f0 error:0 in ollama-runner[408000+163000]

Edit:
I had the timing wrong, it wasn't upon generate, it was upon loading a model

Originally created by @FamousL on GitHub (Dec 4, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1372 Ollama version 0.1.13 Fedora 39 - 6.5.11-300.fc39.x86_64 Ollama runs until I attempt to run a model, then I get this error. This occurs between two different machines, ollama version 0.1.12 works fine. [247685.858191] traps: ollama-runner[16373] trap invalid opcode ip:5012fc sp:7ffd01fd2090 error:0 in ollama-runner[408000+163000] [247896.830423] traps: ollama-runner[49738] trap invalid opcode ip:5012fc sp:7ffd84c37730 error:0 in ollama-runner[408000+163000] [248390.938706] traps: ollama-runner[102749] trap invalid opcode ip:5012fc sp:7ffdfca4d610 error:0 in ollama-runner[408000+163000] [251176.665072] traps: ollama-runner[482136] trap invalid opcode ip:5651efba4730 sp:7ffd1c8c38f0 error:0 in ollama-runner[5651efaa4000+16a000] [251309.955591] traps: ollama-runner[502961] trap invalid opcode ip:561f0918e730 sp:7ffe4b64d630 error:0 in ollama-runner[561f0908e000+16a000] [251451.113782] traps: ollama-runner[524361] trap invalid opcode ip:560c87498730 sp:7ffcb6fe1b90 error:0 in ollama-runner[560c87398000+16a000] [251620.818410] traps: ollama-runner[548566] trap invalid opcode ip:56190fc6b730 sp:7ffeb7c3bff0 error:0 in ollama-runner[56190fb6b000+16a000] [271956.792336] traps: ollama-runner[3942233] trap invalid opcode ip:5012fc sp:7ffe72221110 error:0 in ollama-runner[408000+163000] [271976.986598] traps: ollama-runner[3942286] trap invalid opcode ip:5012fc sp:7ffc06e5b210 error:0 in ollama-runner[408000+163000] [271992.184077] traps: ollama-runner[3942454] trap invalid opcode ip:5012fc sp:7ffcafcd35f0 error:0 in ollama-runner[408000+163000] Edit: I had the timing wrong, it wasn't upon generate, it was upon loading a model
GiteaMirror commented 2026-04-12 10:23:22 -05:00
Author
Owner
Copy Link

@FamousL commented on GitHub (Dec 4, 2023):

View from trying to run a model:
$ ollama run mistral
Error: llama runner process has terminated

<!-- gh-comment-id:1838629110 --> @FamousL commented on GitHub (Dec 4, 2023): View from trying to run a model: $ ollama run mistral Error: llama runner process has terminated
GiteaMirror commented 2026-04-12 10:23:22 -05:00
Author
Owner
Copy Link

@easp commented on GitHub (Dec 4, 2023):

What's are the CPUs in your machine? It looks like Ollama was compiled to use instructions that your CPU doesn't support.

<!-- gh-comment-id:1839025582 --> @easp commented on GitHub (Dec 4, 2023): What's are the CPUs in your machine? It looks like Ollama was compiled to use instructions that your CPU doesn't support.
GiteaMirror commented 2026-04-12 10:23:23 -05:00
Author
Owner
Copy Link

@FamousL commented on GitHub (Dec 4, 2023):

as per /proc/cpuinfo: Intel(R) Xeon(R) CPU X5670 @ 2.93GHz
I also used the curl command provided at ollama.ai to perform the install

Additional information, looks like I was premature in saying 0.1.12 works, it works on my local machine, but not this box.

<!-- gh-comment-id:1839029944 --> @FamousL commented on GitHub (Dec 4, 2023): as per /proc/cpuinfo: Intel(R) Xeon(R) CPU X5670 @ 2.93GHz I also used the curl command provided at ollama.ai to perform the install Additional information, looks like I was premature in saying 0.1.12 works, it works on my local machine, but not this box.
GiteaMirror commented 2026-04-12 10:23:23 -05:00
Author
Owner
Copy Link

@easp commented on GitHub (Dec 4, 2023):

That CPU was released well over a decade ago and does not implement the AVX instruction set, which Ollama is compiled to use.

You could tweak the compiler settings here https://github.com/jmorganca/ollama/blob/main/llm/llama.cpp/generate_linux.go and compile it yourself. There has been talk about making that easier to do, or unnecessary, but that's all you can do for now.

<!-- gh-comment-id:1839460508 --> @easp commented on GitHub (Dec 4, 2023): That CPU was released well over a decade ago and [does not implement the AVX instruction set](https://ark.intel.com/content/www/us/en/ark/products/47920/intel-xeon-processor-x5670-12m-cache-2-93-ghz-6-40-gt-s-intel-qpi.html), which Ollama is compiled to use. You could tweak the compiler settings here https://github.com/jmorganca/ollama/blob/main/llm/llama.cpp/generate_linux.go and compile it yourself. There has been talk about making that easier to do, or unnecessary, but that's all you can do for now.
GiteaMirror commented 2026-04-12 10:23:24 -05:00
Author
Owner
Copy Link

@FamousL commented on GitHub (Dec 4, 2023):

well tha'd do it, apologies for the extra leg work.

<!-- gh-comment-id:1839478831 --> @FamousL commented on GitHub (Dec 4, 2023): well tha'd do it, apologies for the extra leg work.
GiteaMirror commented 2026-04-12 10:23:25 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Dec 4, 2023):

Thanks for answering @eas 👍 , this seems resolved for now.

<!-- gh-comment-id:1839677547 --> @BruceMacD commented on GitHub (Dec 4, 2023): Thanks for answering @eas 👍 , this seems resolved for now.
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#723
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?