github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12160] Issue running ollama on hybrid AMD/Nvidia GPU setup. #54598

New Issue
Closed
opened 2026-04-29 06:30:49 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 06:30:49 -05:00
Owner
Copy Link

Originally created by @Kraust on GitHub (Sep 2, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12160

What is the issue?

Sorry I am new at this and trying to see if local models are a good fit for my use case. I am trying to run with a hybrid Nvidia + AMD setup on OpenSUSE Tumbleweed, and I can get the Nvidia GPU running correctly, but when I also add the AMD iGPU (I assume this is faster than offloading to CPU) there's a panic in a go process.

Relevant log output

https://gist.github.com/Kraust/1034e5f1d9cd35206a75eb4a10be6358

For people who may want to search for this exact issue in the future:

Sep 02 16:13:18 exhaust ollama[2205776]: SIGSEGV: segmentation violation
Sep 02 16:13:18 exhaust ollama[2205776]: PC=0x7fdd01ef9b08 m=0 sigcode=1 addr=0x10
Sep 02 16:13:18 exhaust ollama[2205776]: signal arrived during cgo execution
Sep 02 16:13:18 exhaust ollama[2205776]: goroutine 1 gp=0xc000002380 m=0 mp=0x55f96798ad20 [syscall]:
Sep 02 16:13:18 exhaust ollama[2205776]: runtime.cgocall(0x55f96692d1c0, 0xc000131710)
Sep 02 16:13:18 exhaust ollama[2205776]:         runtime/cgocall.go:167 +0x4b fp=0xc0001316e8 sp=0xc0001316b0 pc=0x55f965c3d3eb
Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/ml/backend/ggml/ggml/src._Cfunc_ggml_backend_load_all_from_path(0x55f98db12970)
Sep 02 16:13:18 exhaust ollama[2205776]:         _cgo_gotypes.go:195 +0x3e fp=0xc000131710 sp=0xc0001316e8 pc=0x55f965fea67e
Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1.1({0xc000038064, 0x15})
Sep 02 16:13:18 exhaust ollama[2205776]:         github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:97 +0xf5 fp=0xc0001317a8 sp=0xc000131710 pc=0x55f965fea115
Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1()
Sep 02 16:13:18 exhaust ollama[2205776]:         github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:98 +0x526 fp=0xc000131a38 sp=0xc0001317a8 pc=0x55f965fe9f66
Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func2()
Sep 02 16:13:18 exhaust ollama[2205776]:         sync/oncefunc.go:27 +0x62 fp=0xc000131a80 sp=0xc000131a38 pc=0x55f965fe9962
Sep 02 16:13:18 exhaust ollama[2205776]: sync.(*Once).doSlow(0x0?, 0x0?)
Sep 02 16:13:18 exhaust ollama[2205776]:         sync/once.go:78 +0xab fp=0xc000131ad8 sp=0xc000131a80 pc=0x55f965c524ab
Sep 02 16:13:18 exhaust ollama[2205776]: sync.(*Once).Do(0x0?, 0x0?)
Sep 02 16:13:18 exhaust ollama[2205776]:         sync/once.go:69 +0x19 fp=0xc000131af8 sp=0xc000131ad8 pc=0x55f965c523d9
Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func3()
Sep 02 16:13:18 exhaust ollama[2205776]:         sync/oncefunc.go:32 +0x2d fp=0xc000131b28 sp=0xc000131af8 pc=0x55f965fe98cd
Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/llama.BackendInit()
Sep 02 16:13:18 exhaust ollama[2205776]:         github.com/ollama/ollama/llama/llama.go:61 +0x16 fp=0xc000131b38 sp=0xc000131b28 pc=0x55f965feec36
Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc000034260, 0x4, 0x4})
Sep 02 16:13:18 exhaust ollama[2205776]:         github.com/ollama/ollama/runner/llamarunner/runner.go:866 +0x395 fp=0xc000131d08 sp=0xc000131b38 pc=0x55f9660ba935
Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/runner.Execute({0xc000034250?, 0x0?, 0x0?})
Sep 02 16:13:18 exhaust ollama[2205776]:         github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000131d30 sp=0xc000131d08 pc=0x55f966145434
Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc00004f500?, {0x55f966c00081?, 0x4?, 0x55f966c00085?})
Sep 02 16:13:18 exhaust ollama[2205776]:         github.com/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc000131d58 sp=0xc000131d30 pc=0x55f9668aa6e5
Sep 02 16:13:18 exhaust ollama[2205776]: github.com/spf13/cobra.(*Command).execute(0xc0004fcf08, {0xc0004593c0, 0x4, 0x4})
Sep 02 16:13:18 exhaust ollama[2205776]:         github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000131e78 sp=0xc000131d58 pc=0x55f965db889c
Sep 02 16:13:18 exhaust ollama[2205776]: github.com/spf13/cobra.(*Command).ExecuteC(0xc0004ce908)
Sep 02 16:13:18 exhaust ollama[2205776]:         github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000131f30 sp=0xc000131e78 pc=0x55f965db90e5
Sep 02 16:13:18 exhaust ollama[2205776]: github.com/spf13/cobra.(*Command).Execute(...)
Sep 02 16:13:18 exhaust ollama[2205776]:         github.com/spf13/cobra@v1.7.0/command.go:992
Sep 02 16:13:18 exhaust ollama[2205776]: github.com/spf13/cobra.(*Command).ExecuteContext(...)
Sep 02 16:13:18 exhaust ollama[2205776]:         github.com/spf13/cobra@v1.7.0/command.go:985
Sep 02 16:13:18 exhaust ollama[2205776]: main.main()

Note my service:

[Unit]
Description=Ollama Service
After=network-online.target

[Service]
ExecStart=/usr/local/bin/ollama serve
User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="OLLAMA_DEBUG=1"
Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0"

[Install]
WantedBy=default.target

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.11.8

Originally created by @Kraust on GitHub (Sep 2, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12160 ### What is the issue? Sorry I am new at this and trying to see if local models are a good fit for my use case. I am trying to run with a hybrid Nvidia + AMD setup on OpenSUSE Tumbleweed, and I can get the Nvidia GPU running correctly, but when I also add the AMD iGPU (I assume this is faster than offloading to CPU) there's a panic in a go process. ### Relevant log output https://gist.github.com/Kraust/1034e5f1d9cd35206a75eb4a10be6358 For people who may want to search for this exact issue in the future: ```shell Sep 02 16:13:18 exhaust ollama[2205776]: SIGSEGV: segmentation violation Sep 02 16:13:18 exhaust ollama[2205776]: PC=0x7fdd01ef9b08 m=0 sigcode=1 addr=0x10 Sep 02 16:13:18 exhaust ollama[2205776]: signal arrived during cgo execution Sep 02 16:13:18 exhaust ollama[2205776]: goroutine 1 gp=0xc000002380 m=0 mp=0x55f96798ad20 [syscall]: Sep 02 16:13:18 exhaust ollama[2205776]: runtime.cgocall(0x55f96692d1c0, 0xc000131710) Sep 02 16:13:18 exhaust ollama[2205776]: runtime/cgocall.go:167 +0x4b fp=0xc0001316e8 sp=0xc0001316b0 pc=0x55f965c3d3eb Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/ml/backend/ggml/ggml/src._Cfunc_ggml_backend_load_all_from_path(0x55f98db12970) Sep 02 16:13:18 exhaust ollama[2205776]: _cgo_gotypes.go:195 +0x3e fp=0xc000131710 sp=0xc0001316e8 pc=0x55f965fea67e Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1.1({0xc000038064, 0x15}) Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:97 +0xf5 fp=0xc0001317a8 sp=0xc000131710 pc=0x55f965fea115 Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1() Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:98 +0x526 fp=0xc000131a38 sp=0xc0001317a8 pc=0x55f965fe9f66 Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func2() Sep 02 16:13:18 exhaust ollama[2205776]: sync/oncefunc.go:27 +0x62 fp=0xc000131a80 sp=0xc000131a38 pc=0x55f965fe9962 Sep 02 16:13:18 exhaust ollama[2205776]: sync.(*Once).doSlow(0x0?, 0x0?) Sep 02 16:13:18 exhaust ollama[2205776]: sync/once.go:78 +0xab fp=0xc000131ad8 sp=0xc000131a80 pc=0x55f965c524ab Sep 02 16:13:18 exhaust ollama[2205776]: sync.(*Once).Do(0x0?, 0x0?) Sep 02 16:13:18 exhaust ollama[2205776]: sync/once.go:69 +0x19 fp=0xc000131af8 sp=0xc000131ad8 pc=0x55f965c523d9 Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func3() Sep 02 16:13:18 exhaust ollama[2205776]: sync/oncefunc.go:32 +0x2d fp=0xc000131b28 sp=0xc000131af8 pc=0x55f965fe98cd Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/llama.BackendInit() Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/llama/llama.go:61 +0x16 fp=0xc000131b38 sp=0xc000131b28 pc=0x55f965feec36 Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc000034260, 0x4, 0x4}) Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/runner/llamarunner/runner.go:866 +0x395 fp=0xc000131d08 sp=0xc000131b38 pc=0x55f9660ba935 Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/runner.Execute({0xc000034250?, 0x0?, 0x0?}) Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000131d30 sp=0xc000131d08 pc=0x55f966145434 Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc00004f500?, {0x55f966c00081?, 0x4?, 0x55f966c00085?}) Sep 02 16:13:18 exhaust ollama[2205776]: github.com/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc000131d58 sp=0xc000131d30 pc=0x55f9668aa6e5 Sep 02 16:13:18 exhaust ollama[2205776]: github.com/spf13/cobra.(*Command).execute(0xc0004fcf08, {0xc0004593c0, 0x4, 0x4}) Sep 02 16:13:18 exhaust ollama[2205776]: github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000131e78 sp=0xc000131d58 pc=0x55f965db889c Sep 02 16:13:18 exhaust ollama[2205776]: github.com/spf13/cobra.(*Command).ExecuteC(0xc0004ce908) Sep 02 16:13:18 exhaust ollama[2205776]: github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000131f30 sp=0xc000131e78 pc=0x55f965db90e5 Sep 02 16:13:18 exhaust ollama[2205776]: github.com/spf13/cobra.(*Command).Execute(...) Sep 02 16:13:18 exhaust ollama[2205776]: github.com/spf13/cobra@v1.7.0/command.go:992 Sep 02 16:13:18 exhaust ollama[2205776]: github.com/spf13/cobra.(*Command).ExecuteContext(...) Sep 02 16:13:18 exhaust ollama[2205776]: github.com/spf13/cobra@v1.7.0/command.go:985 Sep 02 16:13:18 exhaust ollama[2205776]: main.main() ``` Note my service: ``` [Unit] Description=Ollama Service After=network-online.target [Service] ExecStart=/usr/local/bin/ollama serve User=ollama Group=ollama Restart=always RestartSec=3 Environment="OLLAMA_DEBUG=1" Environment="HSA_OVERRIDE_GFX_VERSION=10.3.0" [Install] WantedBy=default.target ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.11.8
GiteaMirror added the bug label 2026-04-29 06:30:49 -05:00
GiteaMirror commented 2026-04-29 06:30:54 -05:00
Author
Owner
Copy Link

@Kraust commented on GitHub (Sep 2, 2025):

Note I am going through https://github.com/ollama/ollama/blob/main/docs/linux.md and manually reinstalling. I will try and go back to an older version and see if it resolves my issue.

<!-- gh-comment-id:3246682010 --> @Kraust commented on GitHub (Sep 2, 2025): Note I am going through https://github.com/ollama/ollama/blob/main/docs/linux.md and manually reinstalling. I will try and go back to an older version and see if it resolves my issue.
GiteaMirror commented 2026-04-29 06:30:55 -05:00
Author
Owner
Copy Link

@Kraust commented on GitHub (Sep 2, 2025):

Resolved in https://github.com/ollama/ollama/releases/tag/v0.11.9-rc0 👍

<!-- gh-comment-id:3246690934 --> @Kraust commented on GitHub (Sep 2, 2025): Resolved in https://github.com/ollama/ollama/releases/tag/v0.11.9-rc0 👍
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#54598
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?