ollama - 💡(How to fix) Fix failure during GPU discovery with ROCm (crash) in ubuntu 26.04 and docker container [1 comments, 1 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#15762Fetched 2026-04-23 07:23:16
View on GitHub
Comments
1
Participants
1
Timeline
5
Reactions
0
Author
Participants
Timeline (top)
renamed ×3commented ×1labeled ×1

Error Message

time=2026-04-23T01:57:05.334Z level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:0]" error="runner crashed"

Code Example

time=2026-04-23T01:57:05.334Z level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:0]" error="runner crashed"
RAW_BUFFERClick to expand / collapse

What is the issue?

Running ROCm in an LXD container installed from official ubuntu repositories for 26.04 (apt install rocm) and the GPU gets properly recognized.

Launching ollama (installed with curl) fails with:

Relevant log output

time=2026-04-23T01:57:05.334Z level=INFO source=runner.go:464 msg="failure during GPU discovery" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/rocm]" extra_envs="map[GGML_CUDA_INIT:1 ROCR_VISIBLE_DEVICES:0]" error="runner crashed"

It's unclear what the crash is

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.21.1

extent analysis

TL;DR

  • Verify the compatibility of Ollama version 0.21.1 with the ROCm installation in the LXD container.

Guidance

  • Check the official Ollama documentation for supported ROCm versions to ensure compatibility with version 0.21.1.
  • Review the ROCm installation process to confirm that all necessary dependencies are installed and configured correctly.
  • Consider checking the environment variables set by the extra_envs map, such as GGML_CUDA_INIT and ROCR_VISIBLE_DEVICES, to ensure they are correctly configured for the AMD GPU.

Example

  • No specific code snippet is provided due to the lack of detailed information about the crash.

Notes

  • The issue may be related to incompatibility between Ollama and ROCm, or incorrect configuration of environment variables.
  • Further debugging information, such as the output of rocm-smi or rocminfo, may be necessary to determine the root cause of the issue.

Recommendation

  • Apply workaround: Try setting the OLLLAMA_LIBRARY_PATH environment variable to a specific path, such as /usr/local/lib/ollama/rocm, to ensure that Ollama is using the correct ROCm libraries.

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…

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 failure during GPU discovery with ROCm (crash) in ubuntu 26.04 and docker container [1 comments, 1 participants]