github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11985] 500: llama runner process has terminated: exit status 2 #7958

New Issue
Closed
opened 2026-04-12 20:07:55 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 20:07:55 -05:00
Owner
Copy Link

Originally created by @nobbywfc on GitHub (Aug 20, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11985

What is the issue?

Ollama/openwebui issued error shown above and I can not use LLM.

I had updated Nvidia windows driver on 19 Aug and suspect that it caused this trouble. Must I uninstall the current driver from PC and purge all nvidia related settings then reinstall previous version of the driver ?

Relevant log output

Following is error message when trying to start container:
-------
docker start ollama
Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running prestart hook #0: exit status 2, stdout: , stderr: SIGSEGV: segmentation violation
PC=0x7e0e3388eed4 m=0 sigcode=1 addr=0x8
signal arrived during cgo execution
-------
A part of docker logs ollama:

----
looking up nvidia GPU memory"
cuda driver library failed to get device context 2time=2025-08-20T08:52:10.625Z level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
time=2025-08-20T08:52:10.872Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.00440619 runner.size="14.9 GiB" runner.vram="6.6 GiB" runner.parallel=1 runner.pid=246 runner.model=/root/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583
cuda driver library failed to get device context 2time=2025-08-20T08:52:10.873Z level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
time=2025-08-20T08:52:11.123Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.255027316 runner.size="14.9 GiB" runner.vram="6.6 GiB" runner.parallel=1 runner.pid=246 runner.model=/root/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583
cuda driver library failed to get device context 2time=2025-08-20T08:52:11.127Z level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
time=2025-08-20T08:52:11.374Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.505478104 runner.size="14.9 GiB" runner.vram="6.6 GiB" runner.parallel=1 runner.pid=246 runner.model=/root/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583
----

OS

Docker

GPU

Nvidia

CPU

Intel

Ollama version

As ollama stopped, I can not find the version.

Originally created by @nobbywfc on GitHub (Aug 20, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11985 ### What is the issue? Ollama/openwebui issued error shown above and I can not use LLM. I had updated Nvidia windows driver on 19 Aug and suspect that it caused this trouble. Must I uninstall the current driver from PC and purge all nvidia related settings then reinstall previous version of the driver ? ### Relevant log output ```shell Following is error message when trying to start container: ------- docker start ollama Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running prestart hook #0: exit status 2, stdout: , stderr: SIGSEGV: segmentation violation PC=0x7e0e3388eed4 m=0 sigcode=1 addr=0x8 signal arrived during cgo execution ------- A part of docker logs ollama: ---- looking up nvidia GPU memory" cuda driver library failed to get device context 2time=2025-08-20T08:52:10.625Z level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" time=2025-08-20T08:52:10.872Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.00440619 runner.size="14.9 GiB" runner.vram="6.6 GiB" runner.parallel=1 runner.pid=246 runner.model=/root/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 cuda driver library failed to get device context 2time=2025-08-20T08:52:10.873Z level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" time=2025-08-20T08:52:11.123Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.255027316 runner.size="14.9 GiB" runner.vram="6.6 GiB" runner.parallel=1 runner.pid=246 runner.model=/root/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 cuda driver library failed to get device context 2time=2025-08-20T08:52:11.127Z level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" time=2025-08-20T08:52:11.374Z level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.505478104 runner.size="14.9 GiB" runner.vram="6.6 GiB" runner.parallel=1 runner.pid=246 runner.model=/root/.ollama/models/blobs/sha256-b112e727c6f18875636c56a779790a590d705aec9e1c0eb5a97d51fc2a778583 ---- ``` ### OS Docker ### GPU Nvidia ### CPU Intel ### Ollama version As ollama stopped, I can not find the version.
GiteaMirror added the bug label 2026-04-12 20:07:55 -05:00
GiteaMirror commented 2026-04-12 20:07:58 -05:00
Author
Owner
Copy Link

@nobbywfc commented on GitHub (Aug 20, 2025):

It's fixed and following is the analysis of Gemini.

The llama runner process has terminated and SIGSEGV errors are often not caused by the model itself, but rather by compatibility issues between the host OS's NVIDIA drivers and the Docker environment (specifically, the NVIDIA Container Toolkit).

The issue was resolved after I updated Docker Desktop, which proves that the problem was indeed related to the host environment.

<!-- gh-comment-id:3207743114 --> @nobbywfc commented on GitHub (Aug 20, 2025): It's fixed and following is the analysis of Gemini. The llama runner process has terminated and SIGSEGV errors are often not caused by the model itself, but rather by compatibility issues between the host OS's NVIDIA drivers and the Docker environment (specifically, the NVIDIA Container Toolkit). The issue was resolved after I updated Docker Desktop, which proves that the problem was indeed related to the host environment.
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#7958
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?