github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #1741] Process 2984649 (ollama-runner) of user 946 dumped core. #26756

New Issue
Closed
opened 2026-04-22 03:18:47 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-22 03:18:47 -05:00
Owner
Copy Link

Originally created by @Alexandrsv on GitHub (Dec 29, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1741

Originally assigned to: @dhiltgen on GitHub.

An error occurs when using WebUI and wizardlm-uncensored:latest

https://pastebin.com/cdvxsEQ7

image

mangaro linux
RTX 4090

Originally created by @Alexandrsv on GitHub (Dec 29, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1741 Originally assigned to: @dhiltgen on GitHub. An error occurs when using WebUI and wizardlm-uncensored:latest https://pastebin.com/cdvxsEQ7 ![image](https://github.com/jmorganca/ollama/assets/15097064/a67a51e3-9a0f-4dc9-9db1-8fcfa81a9fdb) mangaro linux RTX 4090
GiteaMirror added the bug label 2026-04-22 03:18:47 -05:00
GiteaMirror commented 2026-04-22 03:18:50 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Jan 2, 2024):

Hi @Alexandrsv, it looks like you're building from source/pre-release and running Ollama in Docker. Based on the error it could be that Ollama was compiled for the wrong CPU architecture. Are you running this container on an ARM machine such as a Mac or a Raspberry Pi?

Root cause:

дек 30 02:17:31 mj ollama[1322]: llama_new_context_with_model: freq_scale = 1
дек 30 02:17:32 mj systemd[1]: run-docker-runtime\x2drunc-moby-589bb498255b8b8b5b51dc560730e8ae1e1d5c67bf9ba1ceba8a1c22540085fe-runc.l3kOgV.mount: Deactivated successfully.
дек 30 02:17:36 mj kernel: ollama-runner[2984649]: segfault at 0 ip 0000000000539be6 sp 00007ffcedbba3e0 error 4 in ollama-runner[408000+175000] likely on CPU 8 (core 2, socket 0)
дек 30 02:17:36 mj kernel: Code: da fe ff ff 31 f6 49 8d 94 24 80 01 00 00 48 89 df 4c 89 54 24 10 4c 89 5c 24 18 e8 b4 4a fe ff 4c 8b 5c 24 18 4c 8b 54 24 10 <4c> 8b 00 4c 03 43 08 4d 85 e4 74 3d 4d 8d a0 80 01 00 00 45 31 c9
дек 30 02:17:37 mj systemd[1]: Started Process Core Dump (PID 2984802/UID 0).
дек 30 02:17:43 mj systemd[1]: run-docker-runtime\x2drunc-moby-589bb498255b8b8b5b51dc560730e8ae1e1d5c67bf9ba1ceba8a1c22540085fe-runc.lVRPYN.mount: Deactivated successfully.
дек 30 02:17:54 mj plasmashell[2705484]: [2023-12-30 02:17:54.603] [   ] [debug] autosave no need
дек 30 02:17:59 mj systemd[1]: run-docker-runtime\x2drunc-moby-d3d02aa2aa1b507df5e07243327b2fc89627d937b3b1cf3de4183c4463d4352a-runc.vzn7YS.mount: Deactivated successfully.
дек 30 02:18:03 mj systemd[1]: run-docker-runtime\x2drunc-moby-589bb498255b8b8b5b51dc560730e8ae1e1d5c67bf9ba1ceba8a1c22540085fe-runc.lZauyG.mount: Deactivated successfully.
дек 30 02:18:05 mj systemd-coredump[2984803]: [🡕] Process 2984649 (ollama-runner) of user 946 dumped core.
                                                 
                                                 Stack trace of thread 2984649:
                                                 #0  0x0000000000539be6 n/a (/tmp/ollama505739042/llama.cpp/gguf/build/cpu/bin/ollama-runner + 0x139be6)
                                                 #1  0x000000000053fd55 n/a (/tmp/ollama505739042/llama.cpp/gguf/build/cpu/bin/ollama-runner + 0x13fd55)
                                                 #2  0x00000000004c0213 n/a (/tmp/ollama505739042/llama.cpp/gguf/build/cpu/bin/ollama-runner + 0xc0213)
                                                 #3  0x000000000046e50c n/a (/tmp/ollama505739042/llama.cpp/gguf/build/cpu/bin/ollama-runner + 0x6e50c)
                                                 #4  0x000000000041c693 n/a (/tmp/ollama505739042/llama.cpp/gguf/build/cpu/bin/ollama-runner + 0x1c693)
                                                 #5  0x00007fe488b58cd0 n/a (libc.so.6 + 0x27cd0)
                                                 #6  0x00007fe488b58d8a __libc_start_main (libc.so.6 + 0x27d8a)
                                                 #7  0x00000000004215ee n/a (/tmp/ollama505739042/llama.cpp/gguf/build/cpu/bin/ollama-runner + 0x215ee)
                                                 ELF object binary architecture: AMD x86-64
<!-- gh-comment-id:1874083465 --> @BruceMacD commented on GitHub (Jan 2, 2024): Hi @Alexandrsv, it looks like you're building from source/pre-release and running Ollama in Docker. Based on the error it could be that Ollama was compiled for the wrong CPU architecture. Are you running this container on an ARM machine such as a Mac or a Raspberry Pi? Root cause: ``` дек 30 02:17:31 mj ollama[1322]: llama_new_context_with_model: freq_scale = 1 дек 30 02:17:32 mj systemd[1]: run-docker-runtime\x2drunc-moby-589bb498255b8b8b5b51dc560730e8ae1e1d5c67bf9ba1ceba8a1c22540085fe-runc.l3kOgV.mount: Deactivated successfully. дек 30 02:17:36 mj kernel: ollama-runner[2984649]: segfault at 0 ip 0000000000539be6 sp 00007ffcedbba3e0 error 4 in ollama-runner[408000+175000] likely on CPU 8 (core 2, socket 0) дек 30 02:17:36 mj kernel: Code: da fe ff ff 31 f6 49 8d 94 24 80 01 00 00 48 89 df 4c 89 54 24 10 4c 89 5c 24 18 e8 b4 4a fe ff 4c 8b 5c 24 18 4c 8b 54 24 10 <4c> 8b 00 4c 03 43 08 4d 85 e4 74 3d 4d 8d a0 80 01 00 00 45 31 c9 дек 30 02:17:37 mj systemd[1]: Started Process Core Dump (PID 2984802/UID 0). дек 30 02:17:43 mj systemd[1]: run-docker-runtime\x2drunc-moby-589bb498255b8b8b5b51dc560730e8ae1e1d5c67bf9ba1ceba8a1c22540085fe-runc.lVRPYN.mount: Deactivated successfully. дек 30 02:17:54 mj plasmashell[2705484]: [2023-12-30 02:17:54.603] [ ] [debug] autosave no need дек 30 02:17:59 mj systemd[1]: run-docker-runtime\x2drunc-moby-d3d02aa2aa1b507df5e07243327b2fc89627d937b3b1cf3de4183c4463d4352a-runc.vzn7YS.mount: Deactivated successfully. дек 30 02:18:03 mj systemd[1]: run-docker-runtime\x2drunc-moby-589bb498255b8b8b5b51dc560730e8ae1e1d5c67bf9ba1ceba8a1c22540085fe-runc.lZauyG.mount: Deactivated successfully. дек 30 02:18:05 mj systemd-coredump[2984803]: [🡕] Process 2984649 (ollama-runner) of user 946 dumped core. Stack trace of thread 2984649: #0 0x0000000000539be6 n/a (/tmp/ollama505739042/llama.cpp/gguf/build/cpu/bin/ollama-runner + 0x139be6) #1 0x000000000053fd55 n/a (/tmp/ollama505739042/llama.cpp/gguf/build/cpu/bin/ollama-runner + 0x13fd55) #2 0x00000000004c0213 n/a (/tmp/ollama505739042/llama.cpp/gguf/build/cpu/bin/ollama-runner + 0xc0213) #3 0x000000000046e50c n/a (/tmp/ollama505739042/llama.cpp/gguf/build/cpu/bin/ollama-runner + 0x6e50c) #4 0x000000000041c693 n/a (/tmp/ollama505739042/llama.cpp/gguf/build/cpu/bin/ollama-runner + 0x1c693) #5 0x00007fe488b58cd0 n/a (libc.so.6 + 0x27cd0) #6 0x00007fe488b58d8a __libc_start_main (libc.so.6 + 0x27d8a) #7 0x00000000004215ee n/a (/tmp/ollama505739042/llama.cpp/gguf/build/cpu/bin/ollama-runner + 0x215ee) ELF object binary architecture: AMD x86-64 ```
GiteaMirror commented 2026-04-22 03:18:51 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jan 27, 2024):

@Alexandrsv we've changed around how we load the LLM library since you reported this. Could you try to repro this on the latest release 0.1.22 and see if you still have problems?

<!-- gh-comment-id:1912879448 --> @dhiltgen commented on GitHub (Jan 27, 2024): @Alexandrsv we've changed around how we load the LLM library since you reported this. Could you try to repro this on the latest release 0.1.22 and see if you still have problems?
GiteaMirror commented 2026-04-22 03:18:52 -05:00
Author
Owner
Copy Link

@Alexandrsv commented on GitHub (Jan 27, 2024):

I updated the ollama, checked it, the problem was fixed.
Thank you

<!-- gh-comment-id:1913364929 --> @Alexandrsv commented on GitHub (Jan 27, 2024): I updated the ollama, checked it, the problem was fixed. Thank you
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
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#26756
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?