Issue Station
Sign In
Tools hereToolbox

ollama - 💡(How to fix) Fix GPU is there but fails to be registered [3 comments, 3 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
ollama/ollama#15153•Fetched 2026-04-08 01:52:56
View on GitHub
Comments
3
Participants
3
Timeline
12
Reactions
1
Author
nexxyrusnexxyrus
Participants
mspservicesmspservicesnexxyrusnexxyrusrick-githubrick-github
Timeline (top)
subscribed ×4commented ×3mentioned ×3labeled ×2

Error Message

time=2026-03-31T00:00:56.727+02:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:GPU-3ae513de0b7ca695]" error="failed to finish discovery before timeout"

Code Example

time=2026-03-31T00:00:26.751+02:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/rocm
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
ggml_cuda_init: initializing rocBLAS on device 0
pid:588 tid:0x7f3c0edfb6c0 [hsakmt_hsa_signal_store_screlease] hsa_signal_store_screlease not found - /opt/rocm-7.2.1/lib/librocdxg.so: undefined symbol: hsa_signal_store_screlease
time=2026-03-31T00:00:56.727+02:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:GPU-3ae513de0b7ca695]" error="failed to finish discovery before timeout"
time=2026-03-31T00:00:56.727+02:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" devices=[]
time=2026-03-31T00:00:56.727+02:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=30.001268652s OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:GPU-3ae513de0b7ca695]"
time=2026-03-31T00:00:56.727+02:00 level=DEBUG source=runner.go:153 msg="filtering device which didn't fully initialize" id=GPU-3ae513de0b7ca695 libdir=/usr/lib/ollama/rocm pci_id=0000:03:00.0 library=ROCm
time=2026-03-31T00:00:56.727+02:00 level=TRACE source=runner.go:174 msg="supported GPU library combinations before filtering" supported=map[]
time=2026-03-31T00:00:56.727+02:00 level=TRACE source=runner.go:183 msg="removing unsupported or overlapping GPU combination" libDir=/usr/lib/ollama/rocm description="AMD Radeon RX 9060 XT" compute=gfx1200 pci_id=0000:03:00.0
time=2026-03-31T00:00:56.727+02:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=30.150257536s
time=2026-03-31T00:00:56.727+02:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="15.6 GiB" available="15.0 GiB"
time=2026-03-31T00:00:56.727+02:00 level=INFO source=routes.go:1850 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096
RAW_BUFFERClick to expand / collapse

What is the issue?

Installed rocm and librocdxg via the instructions but it won't work.

Relevant log output

time=2026-03-31T00:00:26.751+02:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/rocm
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
ggml_cuda_init: initializing rocBLAS on device 0
pid:588 tid:0x7f3c0edfb6c0 [hsakmt_hsa_signal_store_screlease] hsa_signal_store_screlease not found - /opt/rocm-7.2.1/lib/librocdxg.so: undefined symbol: hsa_signal_store_screlease
time=2026-03-31T00:00:56.727+02:00 level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:GPU-3ae513de0b7ca695]" error="failed to finish discovery before timeout"
time=2026-03-31T00:00:56.727+02:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" devices=[]
time=2026-03-31T00:00:56.727+02:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=30.001268652s OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:GPU-3ae513de0b7ca695]"
time=2026-03-31T00:00:56.727+02:00 level=DEBUG source=runner.go:153 msg="filtering device which didn't fully initialize" id=GPU-3ae513de0b7ca695 libdir=/usr/lib/ollama/rocm pci_id=0000:03:00.0 library=ROCm
time=2026-03-31T00:00:56.727+02:00 level=TRACE source=runner.go:174 msg="supported GPU library combinations before filtering" supported=map[]
time=2026-03-31T00:00:56.727+02:00 level=TRACE source=runner.go:183 msg="removing unsupported or overlapping GPU combination" libDir=/usr/lib/ollama/rocm description="AMD Radeon RX 9060 XT" compute=gfx1200 pci_id=0000:03:00.0
time=2026-03-31T00:00:56.727+02:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=30.150257536s
time=2026-03-31T00:00:56.727+02:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="15.6 GiB" available="15.0 GiB"
time=2026-03-31T00:00:56.727+02:00 level=INFO source=routes.go:1850 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096

OS

WSL2

GPU

AMD

CPU

AMD

Ollama version

0.19.0

extent analysis

Fix Plan

The issue seems to be related to the ROCm installation and compatibility. To fix this, we need to ensure that the ROCm version is compatible with the AMD GPU and the WSL2 environment.

  • Update the ROCm version to the latest compatible version.
  • Install the necessary dependencies for ROCm, including librocdxg.
  • Set the ROCR_VISIBLE_DEVICES environment variable to the correct GPU device.

Example code to set the environment variable:

export ROCR_VISIBLE_DEVICES=GPU-3ae513de0b7ca695
  • Verify that the librocdxg library is installed and loaded correctly:
ldconfig -v | grep librocdxg

This should show the path to the librocdxg library.

Verification

To verify that the fix worked, restart the Ollama service and check the logs for any errors related to ROCm or GPU discovery.

  • Check the Ollama logs for any errors:
journalctl -u ollama
  • Verify that the GPU is detected correctly:
rocm-smi

This should show the GPU device and its status.

Extra Tips

  • Ensure that the WSL2 environment is up-to-date and compatible with the ROCm version.
  • Check the ROCm documentation for any specific requirements or dependencies for the AMD GPU.
  • If issues persist, try reinstalling ROCm and its dependencies.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#conversation history#tool integration#LLM response#prompt template#agent execution

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

ollama - 💡(How to fix) Fix GPU is there but fails to be registered [3 comments, 3 participants]