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 #9970] RX6600 detected but not used (Linux) #32290

New Issue
Closed
opened 2026-04-22 13:25:00 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 13:25:00 -05:00
Owner
Copy Link

Originally created by @LevitatingBusinessMan on GitHub (Mar 25, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9970

What is the issue?

I run HSA_OVERRIDE_GFX_VERSION=10.3.0 ollama serve, the gpu is seemingly detected. But it still ends up loading a cpu backend.

I am using opensuse and official upstream rocm packages.

Relevant log output

I attached a whole log but here is the relevant stuff:

time=2025-03-25T04:17:20.113+01:00 level=DEBUG source=server.go:343 msg="adding gpu dependency paths" paths=[/opt/rocm/lib]
time=2025-03-25T04:17:20.113+01:00 level=INFO source=server.go:405 msg="starting llama server" cmd="/usr/bin/ollama runner --model /home/rein/.ollama/models/blobs/sha256-aabd4debf0c8f08881923f2c25fc0fdeed24435271c2b3e92c4af36704040dbc --ctx-size 8192 --batch-size 512 --n-gpu-layers 29 --verbose --threads 12 --parallel 4 --port 40801"
time=2025-03-25T04:17:20.113+01:00 level=DEBUG source=server.go:423 msg=subprocess environment="[HSA_OVERRIDE_GFX_VERSION=10.3.0 PATH=/home/rein/go/bin:/home/rein/.local/bin:/home/rein/scripts:/home/rein/.cargo/bin:/home/rein/bin:/home/rein/.config/emacs/bin:/home/rein/.gem/ruby/3.0.0/bin:/usr/local/bin:/bin:/usr/bin LD_LIBRARY_PATH=/opt/rocm/lib:/usr/lib/ollama ROCR_VISIBLE_DEVICES=0]"
time=2025-03-25T04:17:20.113+01:00 level=INFO source=sched.go:450 msg="loaded runners" count=1
time=2025-03-25T04:17:20.113+01:00 level=INFO source=server.go:585 msg="waiting for llama runner to start responding"
time=2025-03-25T04:17:20.113+01:00 level=INFO source=server.go:619 msg="waiting for server to become available" status="llm server error"
time=2025-03-25T04:17:20.120+01:00 level=INFO source=runner.go:931 msg="starting go runner"
time=2025-03-25T04:17:20.120+01:00 level=DEBUG source=ggml.go:93 msg="skipping path which is not part of ollama" path=/opt/rocm/lib
time=2025-03-25T04:17:20.120+01:00 level=DEBUG source=ggml.go:99 msg="ggml backend load all from path" path=/usr/lib/ollama
ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-alderlake.so score: 0
ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-haswell.so score: 55
ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-icelake.so score: 0
ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-sandybridge.so score: 20
ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-skylakex.so score: 0
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.time=2025-03-25T04:17:20.113+01:00 level=DEBUG source=server.go:343 msg="adding gpu dependency paths" paths=[/opt/rocm/lib]
time=2025-03-25T04:17:20.113+01:00 level=INFO source=server.go:405 msg="starting llama server" cmd="/usr/bin/ollama runner --model /home/rein/.ollama/models/blobs/sha256-aabd4debf0c8f08881923f2c25fc0fdeed24435271c2b3e92c4af36704040dbc --ctx-size 8192 --batch-size 512 --n-gpu-layers 29 --verbose --threads 12 --parallel 4 --port 40801"
time=2025-03-25T04:17:20.113+01:00 level=DEBUG source=server.go:423 msg=subprocess environment="[HSA_OVERRIDE_GFX_VERSION=10.3.0 PATH=/home/rein/go/bin:/home/rein/.local/bin:/home/rein/scripts:/home/rein/.cargo/bin:/home/rein/bin:/home/rein/.config/emacs/bin:/home/rein/.gem/ruby/3.0.0/bin:/usr/local/bin:/bin:/usr/bin LD_LIBRARY_PATH=/opt/rocm/lib:/usr/lib/ollama ROCR_VISIBLE_DEVICES=0]"
time=2025-03-25T04:17:20.113+01:00 level=INFO source=sched.go:450 msg="loaded runners" count=1
time=2025-03-25T04:17:20.113+01:00 level=INFO source=server.go:585 msg="waiting for llama runner to start responding"
time=2025-03-25T04:17:20.113+01:00 level=INFO source=server.go:619 msg="waiting for server to become available" status="llm server error"
time=2025-03-25T04:17:20.120+01:00 level=INFO source=runner.go:931 msg="starting go runner"
time=2025-03-25T04:17:20.120+01:00 level=DEBUG source=ggml.go:93 msg="skipping path which is not part of ollama" path=/opt/rocm/lib
time=2025-03-25T04:17:20.120+01:00 level=DEBUG source=ggml.go:99 msg="ggml backend load all from path" path=/usr/lib/ollama
ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-alderlake.so score: 0
ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-haswell.so score: 55
ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-icelake.so score: 0
ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-sandybridge.so score: 20
ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-skylakex.so score: 0
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.

I am guessing this could have something to do with it:
time=2025-03-25T04:17:20.120+01:00 level=DEBUG source=ggml.go:93 msg="skipping path which is not part of ollama" path=/opt/rocm/lib

log.txt


### OS

Linux

### GPU

AMD

### CPU

AMD

### Ollama version

0.6.0
Originally created by @LevitatingBusinessMan on GitHub (Mar 25, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9970 ### What is the issue? I run `HSA_OVERRIDE_GFX_VERSION=10.3.0 ollama serve`, the gpu is seemingly detected. But it still ends up loading a cpu backend. I am using opensuse and official upstream rocm packages. ### Relevant log output ```shell I attached a whole log but here is the relevant stuff: time=2025-03-25T04:17:20.113+01:00 level=DEBUG source=server.go:343 msg="adding gpu dependency paths" paths=[/opt/rocm/lib] time=2025-03-25T04:17:20.113+01:00 level=INFO source=server.go:405 msg="starting llama server" cmd="/usr/bin/ollama runner --model /home/rein/.ollama/models/blobs/sha256-aabd4debf0c8f08881923f2c25fc0fdeed24435271c2b3e92c4af36704040dbc --ctx-size 8192 --batch-size 512 --n-gpu-layers 29 --verbose --threads 12 --parallel 4 --port 40801" time=2025-03-25T04:17:20.113+01:00 level=DEBUG source=server.go:423 msg=subprocess environment="[HSA_OVERRIDE_GFX_VERSION=10.3.0 PATH=/home/rein/go/bin:/home/rein/.local/bin:/home/rein/scripts:/home/rein/.cargo/bin:/home/rein/bin:/home/rein/.config/emacs/bin:/home/rein/.gem/ruby/3.0.0/bin:/usr/local/bin:/bin:/usr/bin LD_LIBRARY_PATH=/opt/rocm/lib:/usr/lib/ollama ROCR_VISIBLE_DEVICES=0]" time=2025-03-25T04:17:20.113+01:00 level=INFO source=sched.go:450 msg="loaded runners" count=1 time=2025-03-25T04:17:20.113+01:00 level=INFO source=server.go:585 msg="waiting for llama runner to start responding" time=2025-03-25T04:17:20.113+01:00 level=INFO source=server.go:619 msg="waiting for server to become available" status="llm server error" time=2025-03-25T04:17:20.120+01:00 level=INFO source=runner.go:931 msg="starting go runner" time=2025-03-25T04:17:20.120+01:00 level=DEBUG source=ggml.go:93 msg="skipping path which is not part of ollama" path=/opt/rocm/lib time=2025-03-25T04:17:20.120+01:00 level=DEBUG source=ggml.go:99 msg="ggml backend load all from path" path=/usr/lib/ollama ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-alderlake.so score: 0 ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-haswell.so score: 55 ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-icelake.so score: 0 ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-sandybridge.so score: 20 ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-skylakex.so score: 0 load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.time=2025-03-25T04:17:20.113+01:00 level=DEBUG source=server.go:343 msg="adding gpu dependency paths" paths=[/opt/rocm/lib] time=2025-03-25T04:17:20.113+01:00 level=INFO source=server.go:405 msg="starting llama server" cmd="/usr/bin/ollama runner --model /home/rein/.ollama/models/blobs/sha256-aabd4debf0c8f08881923f2c25fc0fdeed24435271c2b3e92c4af36704040dbc --ctx-size 8192 --batch-size 512 --n-gpu-layers 29 --verbose --threads 12 --parallel 4 --port 40801" time=2025-03-25T04:17:20.113+01:00 level=DEBUG source=server.go:423 msg=subprocess environment="[HSA_OVERRIDE_GFX_VERSION=10.3.0 PATH=/home/rein/go/bin:/home/rein/.local/bin:/home/rein/scripts:/home/rein/.cargo/bin:/home/rein/bin:/home/rein/.config/emacs/bin:/home/rein/.gem/ruby/3.0.0/bin:/usr/local/bin:/bin:/usr/bin LD_LIBRARY_PATH=/opt/rocm/lib:/usr/lib/ollama ROCR_VISIBLE_DEVICES=0]" time=2025-03-25T04:17:20.113+01:00 level=INFO source=sched.go:450 msg="loaded runners" count=1 time=2025-03-25T04:17:20.113+01:00 level=INFO source=server.go:585 msg="waiting for llama runner to start responding" time=2025-03-25T04:17:20.113+01:00 level=INFO source=server.go:619 msg="waiting for server to become available" status="llm server error" time=2025-03-25T04:17:20.120+01:00 level=INFO source=runner.go:931 msg="starting go runner" time=2025-03-25T04:17:20.120+01:00 level=DEBUG source=ggml.go:93 msg="skipping path which is not part of ollama" path=/opt/rocm/lib time=2025-03-25T04:17:20.120+01:00 level=DEBUG source=ggml.go:99 msg="ggml backend load all from path" path=/usr/lib/ollama ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-alderlake.so score: 0 ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-haswell.so score: 55 ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-icelake.so score: 0 ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-sandybridge.so score: 20 ggml_backend_load_best: /usr/lib/ollama/libggml-cpu-skylakex.so score: 0 load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell. ``` I am guessing this could have something to do with it: `time=2025-03-25T04:17:20.120+01:00 level=DEBUG source=ggml.go:93 msg="skipping path which is not part of ollama" path=/opt/rocm/lib` [log.txt](https://github.com/user-attachments/files/19441190/out.txt) ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.6.0
GiteaMirror added the bug label 2026-04-22 13:25:00 -05:00
GiteaMirror commented 2026-04-22 13:25:03 -05:00
Author
Owner
Copy Link

@LevitatingBusinessMan commented on GitHub (Mar 25, 2025):

I forgot to install the rocm lib tarball

<!-- gh-comment-id:2750008708 --> @LevitatingBusinessMan commented on GitHub (Mar 25, 2025): I forgot to install the rocm lib tarball
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#32290
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?