github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13011] Ollama 0.12.10: After starting the service, my computer hangs when trying to suspend #34374

New Issue
Closed
opened 2026-04-22 17:52:44 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 17:52:44 -05:00
Owner
Copy Link

Originally created by @mfil on GitHub (Nov 8, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13011

What is the issue?

After upgrading the ollama and ollama-rocm packages to version 0.12.9, I encountered a problem with systemctl suspend. It also happens with version 0.12.10. I did not have this problem with 0.12.3.

What happens is, if the ollama service has been started, the computer doesn't suspend but becomes unresponsive when I run systemctl suspend. The screen is still on and displaying the last image, all fans are running, but the computer is not reacting to any keyboard or mouse inputs. I can't connect to it with ssh anymore either.

I can fix suspend by disabling the ollama service and rebooting. Just stopping the service is not enough.

The GPU is a AMD Radeon RX 6800. After starting the service, I see some error logs from the amdgpu driver, which I did not see with 0.12.3. I'm including both the ollama and kernel logs.

Please let me know if you need any additional information!

Relevant log output

Nov 08 02:31:18 orion systemd[1]: Started Ollama Service.
Nov 08 02:31:18 orion sudo[20748]: pam_unix(sudo:session): session closed for user root
Nov 08 02:31:19 orion ollama[20816]: time=2025-11-08T02:31:19.020+01:00 level=INFO source=routes.go:1525 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/var/lib/ollama OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
Nov 08 02:31:19 orion ollama[20816]: time=2025-11-08T02:31:19.024+01:00 level=INFO source=images.go:522 msg="total blobs: 32"
Nov 08 02:31:19 orion ollama[20816]: time=2025-11-08T02:31:19.025+01:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
Nov 08 02:31:19 orion ollama[20816]: time=2025-11-08T02:31:19.025+01:00 level=INFO source=routes.go:1578 msg="Listening on 127.0.0.1:11434 (version 0.12.10)"
Nov 08 02:31:19 orion ollama[20816]: time=2025-11-08T02:31:19.025+01:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
Nov 08 02:31:19 orion ollama[20816]: time=2025-11-08T02:31:19.026+01:00 level=INFO source=server.go:400 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 33927"
Nov 08 02:31:24 orion sudo[20844]:      max : TTY=pts/0 ; PWD=/home/max ; USER=root ; COMMAND=/usr/bin/journalctl
Nov 08 02:31:24 orion sudo[20844]: pam_unix(sudo:session): session opened for user root(uid=0) by max(uid=1000)
Nov 08 02:31:24 orion ollama[20816]: time=2025-11-08T02:31:24.929+01:00 level=INFO source=server.go:400 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 39207"
Nov 08 02:31:24 orion kernel: [drm:amdgpu_job_submit [amdgpu]] *ERROR* Trying to push to a killed entity
Nov 08 02:31:30 orion ollama[20816]: time=2025-11-08T02:31:30.678+01:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-5c524287c5b93dbe filter_id="" library=ROCm compute=gfx1030 name=ROCm0 description="AMD Radeon RX 6800" libdirs=ollama driver=60443.48 pci_id=0000:03:00.0 type=discrete total="16.0 GiB" available="15.9 GiB"
Nov 08 02:31:30 orion ollama[20816]: time=2025-11-08T02:31:30.678+01:00 level=INFO source=routes.go:1619 msg="entering low vram mode" "total vram"="16.0 GiB" threshold="20.0 GiB"
Nov 08 02:31:30 orion kernel: amdgpu: Freeing queue vital buffer 0x7ff746a00000, queue evicted
Nov 08 02:31:30 orion kernel: [drm:amdgpu_job_submit [amdgpu]] *ERROR* Trying to push to a killed entity

OS

Linux

GPU

AMD

CPU

Intel

Ollama version

0.12.10

Originally created by @mfil on GitHub (Nov 8, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13011 ### What is the issue? After upgrading the ollama and ollama-rocm packages to version 0.12.9, I encountered a problem with `systemctl suspend`. It also happens with version 0.12.10. I did not have this problem with 0.12.3. What happens is, if the ollama service has been started, the computer doesn't suspend but becomes unresponsive when I run `systemctl suspend`. The screen is still on and displaying the last image, all fans are running, but the computer is not reacting to any keyboard or mouse inputs. I can't connect to it with ssh anymore either. I can fix suspend by disabling the ollama service and rebooting. Just stopping the service is not enough. The GPU is a AMD Radeon RX 6800. After starting the service, I see some error logs from the amdgpu driver, which I did not see with 0.12.3. I'm including both the ollama and kernel logs. Please let me know if you need any additional information! ### Relevant log output ```shell Nov 08 02:31:18 orion systemd[1]: Started Ollama Service. Nov 08 02:31:18 orion sudo[20748]: pam_unix(sudo:session): session closed for user root Nov 08 02:31:19 orion ollama[20816]: time=2025-11-08T02:31:19.020+01:00 level=INFO source=routes.go:1525 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/var/lib/ollama OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" Nov 08 02:31:19 orion ollama[20816]: time=2025-11-08T02:31:19.024+01:00 level=INFO source=images.go:522 msg="total blobs: 32" Nov 08 02:31:19 orion ollama[20816]: time=2025-11-08T02:31:19.025+01:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" Nov 08 02:31:19 orion ollama[20816]: time=2025-11-08T02:31:19.025+01:00 level=INFO source=routes.go:1578 msg="Listening on 127.0.0.1:11434 (version 0.12.10)" Nov 08 02:31:19 orion ollama[20816]: time=2025-11-08T02:31:19.025+01:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." Nov 08 02:31:19 orion ollama[20816]: time=2025-11-08T02:31:19.026+01:00 level=INFO source=server.go:400 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 33927" Nov 08 02:31:24 orion sudo[20844]: max : TTY=pts/0 ; PWD=/home/max ; USER=root ; COMMAND=/usr/bin/journalctl Nov 08 02:31:24 orion sudo[20844]: pam_unix(sudo:session): session opened for user root(uid=0) by max(uid=1000) Nov 08 02:31:24 orion ollama[20816]: time=2025-11-08T02:31:24.929+01:00 level=INFO source=server.go:400 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 39207" Nov 08 02:31:24 orion kernel: [drm:amdgpu_job_submit [amdgpu]] *ERROR* Trying to push to a killed entity Nov 08 02:31:30 orion ollama[20816]: time=2025-11-08T02:31:30.678+01:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-5c524287c5b93dbe filter_id="" library=ROCm compute=gfx1030 name=ROCm0 description="AMD Radeon RX 6800" libdirs=ollama driver=60443.48 pci_id=0000:03:00.0 type=discrete total="16.0 GiB" available="15.9 GiB" Nov 08 02:31:30 orion ollama[20816]: time=2025-11-08T02:31:30.678+01:00 level=INFO source=routes.go:1619 msg="entering low vram mode" "total vram"="16.0 GiB" threshold="20.0 GiB" Nov 08 02:31:30 orion kernel: amdgpu: Freeing queue vital buffer 0x7ff746a00000, queue evicted Nov 08 02:31:30 orion kernel: [drm:amdgpu_job_submit [amdgpu]] *ERROR* Trying to push to a killed entity ``` ### OS Linux ### GPU AMD ### CPU Intel ### Ollama version 0.12.10
GiteaMirror added the bug label 2026-04-22 17:52:44 -05:00
GiteaMirror commented 2026-04-22 17:52:45 -05:00
Author
Owner
Copy Link

@mfil commented on GitHub (Nov 28, 2025):

Updated to 0.13.0 and the problem is gone!

<!-- gh-comment-id:3589831889 --> @mfil commented on GitHub (Nov 28, 2025): Updated to 0.13.0 and the problem is gone!
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#34374
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?