github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-21 13:11:39 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #12117] ROCM crash when loading model #8053

New Issue
Closed
opened 2026-04-12 20:18:29 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 20:18:29 -05:00
Owner
Copy Link

Originally created by @artemklevtsov on GitHub (Aug 29, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12117

What is the issue?

Ollama crash when trying to interact with model.

❯ ollama run llama3.1:8b
>>> Test
Error: model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details

Linux kernel version:

❯ uname -r 
6.16.3-zen1-1.1-zen

Kernel cmdline:

❯ cat /proc/cmdline 
amd_pstate=active mdgpu.mcbp=0 amdgpu.ppfeaturemask=0xffffffff root=UUID=a090f7ee-aec4-46df-819a-8bcc28538cd6 rw rootflags=subvol=/@

Arch Linux packages:

❯ pacman -Qs rocm | grep 'local/'
local/hipblas 6.4.3-1
local/hsa-rocr 6.4.3-1
local/ollama-rocm 0.11.4-1
local/rocblas 6.4.3-1
local/rocm-core 6.4.3-1
local/rocm-device-libs 6.4.3-1
local/rocm-llvm 6.4.3-1
local/rocminfo 6.4.3-1
local/rocsolver 6.4.3-1
local/rocsparse 6.4.3-1.1
local/roctracer 6.4.3-1.1

ollama.log

Note: works with docker.

docker run --rm --device /dev/kfd --device /dev/dri -p 11434:11434 --name ollama ollama/ollama:rocm

Relevant log output

time=2025-08-29T19:03:09.177+07:00 level=INFO source=server.go:637 msg="llama runner started in 7.27 seconds"
time=2025-08-29T19:03:09.177+07:00 level=DEBUG source=sched.go:493 msg="finished setting up" runner.name=registry.ollama.ai/library/llama3.1:8b runner.inference=rocm runner.devices=1 runner.size="5.7 GiB" runner.vram="5.7 GiB" runner.parallel=1 runner.pid=432697 runner.model=/home/unikum/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 runner.num_ctx=4096
[GIN] 2025/08/29 - 19:03:09 | 200 |  7.473828313s |       127.0.0.1 | POST     "/api/generate"
time=2025-08-29T19:03:09.177+07:00 level=DEBUG source=sched.go:501 msg="context for request finished"
time=2025-08-29T19:03:09.177+07:00 level=DEBUG source=sched.go:341 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/llama3.1:8b runner.inference=rocm runner.devices=1 runner.size="5.7 GiB" runner.vram="5.7 GiB" runner.parallel=1 runner.pid=432697 runner.model=/home/unikum/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 runner.num_ctx=4096 duration=5m0s
time=2025-08-29T19:03:09.177+07:00 level=DEBUG source=sched.go:359 msg="after processing request finished event" runner.name=registry.ollama.ai/library/llama3.1:8b runner.inference=rocm runner.devices=1 runner.size="5.7 GiB" runner.vram="5.7 GiB" runner.parallel=1 runner.pid=432697 runner.model=/home/unikum/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 runner.num_ctx=4096 refCount=0
time=2025-08-29T19:03:13.112+07:00 level=DEBUG source=sched.go:613 msg="evaluating already loaded" model=/home/unikum/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29
time=2025-08-29T19:03:13.112+07:00 level=DEBUG source=server.go:736 msg="completion request" images=0 prompt=103 format=""
time=2025-08-29T19:03:13.112+07:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=11 used=0 remaining=11
SIGSEGV: segmentation violation
PC=0x7f107408d53b m=4 sigcode=1 addr=0x28
signal arrived during cgo execution

goroutine 51 gp=0xc000505180 m=4 mp=0xc00009d808 [syscall]:
runtime.cgocall(0x563b2a5f2a10, 0xc0000abbd8)

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.11.4

Originally created by @artemklevtsov on GitHub (Aug 29, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12117 ### What is the issue? Ollama crash when trying to interact with model. ```sh ❯ ollama run llama3.1:8b >>> Test Error: model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details ``` Linux kernel version: ```sh ❯ uname -r 6.16.3-zen1-1.1-zen ``` Kernel cmdline: ```sh ❯ cat /proc/cmdline amd_pstate=active mdgpu.mcbp=0 amdgpu.ppfeaturemask=0xffffffff root=UUID=a090f7ee-aec4-46df-819a-8bcc28538cd6 rw rootflags=subvol=/@ ``` Arch Linux packages: ```sh ❯ pacman -Qs rocm | grep 'local/' local/hipblas 6.4.3-1 local/hsa-rocr 6.4.3-1 local/ollama-rocm 0.11.4-1 local/rocblas 6.4.3-1 local/rocm-core 6.4.3-1 local/rocm-device-libs 6.4.3-1 local/rocm-llvm 6.4.3-1 local/rocminfo 6.4.3-1 local/rocsolver 6.4.3-1 local/rocsparse 6.4.3-1.1 local/roctracer 6.4.3-1.1 ``` [ollama.log](https://github.com/user-attachments/files/22045016/ollama.log) Note: **works with docker**. ```sh docker run --rm --device /dev/kfd --device /dev/dri -p 11434:11434 --name ollama ollama/ollama:rocm ``` ### Relevant log output ```shell time=2025-08-29T19:03:09.177+07:00 level=INFO source=server.go:637 msg="llama runner started in 7.27 seconds" time=2025-08-29T19:03:09.177+07:00 level=DEBUG source=sched.go:493 msg="finished setting up" runner.name=registry.ollama.ai/library/llama3.1:8b runner.inference=rocm runner.devices=1 runner.size="5.7 GiB" runner.vram="5.7 GiB" runner.parallel=1 runner.pid=432697 runner.model=/home/unikum/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 runner.num_ctx=4096 [GIN] 2025/08/29 - 19:03:09 | 200 | 7.473828313s | 127.0.0.1 | POST "/api/generate" time=2025-08-29T19:03:09.177+07:00 level=DEBUG source=sched.go:501 msg="context for request finished" time=2025-08-29T19:03:09.177+07:00 level=DEBUG source=sched.go:341 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/llama3.1:8b runner.inference=rocm runner.devices=1 runner.size="5.7 GiB" runner.vram="5.7 GiB" runner.parallel=1 runner.pid=432697 runner.model=/home/unikum/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 runner.num_ctx=4096 duration=5m0s time=2025-08-29T19:03:09.177+07:00 level=DEBUG source=sched.go:359 msg="after processing request finished event" runner.name=registry.ollama.ai/library/llama3.1:8b runner.inference=rocm runner.devices=1 runner.size="5.7 GiB" runner.vram="5.7 GiB" runner.parallel=1 runner.pid=432697 runner.model=/home/unikum/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 runner.num_ctx=4096 refCount=0 time=2025-08-29T19:03:13.112+07:00 level=DEBUG source=sched.go:613 msg="evaluating already loaded" model=/home/unikum/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 time=2025-08-29T19:03:13.112+07:00 level=DEBUG source=server.go:736 msg="completion request" images=0 prompt=103 format="" time=2025-08-29T19:03:13.112+07:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=11 used=0 remaining=11 SIGSEGV: segmentation violation PC=0x7f107408d53b m=4 sigcode=1 addr=0x28 signal arrived during cgo execution goroutine 51 gp=0xc000505180 m=4 mp=0xc00009d808 [syscall]: runtime.cgocall(0x563b2a5f2a10, 0xc0000abbd8) ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.11.4
GiteaMirror added the bug label 2026-04-12 20:18:29 -05:00
GiteaMirror commented 2026-04-12 20:18:30 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 29, 2025):

https://gitlab.archlinux.org/archlinux/packaging/packages/ollama/-/issues/19

<!-- gh-comment-id:3236994800 --> @rick-github commented on GitHub (Aug 29, 2025): https://gitlab.archlinux.org/archlinux/packaging/packages/ollama/-/issues/19
GiteaMirror commented 2026-04-12 20:18:30 -05:00
Author
Owner
Copy Link

@artemklevtsov commented on GitHub (Aug 29, 2025):

Thank for the link. With downgraded hipblas ollama works.

<!-- gh-comment-id:3237252617 --> @artemklevtsov commented on GitHub (Aug 29, 2025): Thank for the link. With downgraded `hipblas` ollama works.
GiteaMirror commented 2026-04-12 20:18:31 -05:00
Author
Owner
Copy Link

@artemklevtsov commented on GitHub (Aug 29, 2025):

Solved after last packages update.

<!-- gh-comment-id:3237497528 --> @artemklevtsov commented on GitHub (Aug 29, 2025): Solved after last packages update.
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#8053
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?