Skip to content

Added GPU-Access to systemd-Service Definition #10694

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Aug 12, 2025
Merged

Added GPU-Access to systemd-Service Definition #10694

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
e4bec33
Update parent title for install and configure benchmark pages (#10686)
kolchfa-aws Aug 8, 2025
ec281c5
Delete unused images from the site and correct image formatting (#10691)
kolchfa-aws Aug 8, 2025
c0836f0
Added GPU-Access for systemd
Aug 9, 2025
1025e81
Merge branch 'main' into main
kolchfa-aws Aug 11, 2025
930ec42
Update _ml-commons-plugin/gpu-acceleration.md
TheBigK02 Aug 12, 2025
c76ed5e
Update _ml-commons-plugin/gpu-acceleration.md
TheBigK02 Aug 12, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions _ml-commons-plugin/gpu-acceleration.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,6 +67,18 @@
fi
```

If you run OpenSearch natively (without Docker) using the packaged version of OpenSearch, `systemd` may block OpenSearch from accessing your GPU. To accelerate models, you need a working [CUDA Toolkit](https://developer.nvidia.com/cuda-toolkit) installation and access to the NVIDIA device under `/dev`.

To allow OpenSearch to use the GPU, update the `systemd` service by adding the following configuration:

```ini
systemctl edit opensearch.service

Check failure on line 75 in _ml-commons-plugin/gpu-acceleration.md

View workflow job for this annotation

GitHub Actions / style-job 

[vale] reported by reviewdog 🐶
[OpenSearch.Spelling] Error: opensearch. If you are referencing a setting, variable, format, function, or repository, surround it with tic marks.

Raw Output:
{"message": "[OpenSearch.Spelling] Error: opensearch. If you are referencing a setting, variable, format, function, or repository, surround it with tic marks.", "location": {"path": "_ml-commons-plugin/gpu-acceleration.md", "range": {"start": {"line": 75, "column": 16}}}, "severity": "ERROR"}

Check failure on line 75 in _ml-commons-plugin/gpu-acceleration.md

View workflow job for this annotation

GitHub Actions / style-job 

[vale] reported by reviewdog 🐶
[Vale.Terms] Use 'OpenSearch' instead of 'opensearch'.

Raw Output:
{"message": "[Vale.Terms] Use 'OpenSearch' instead of 'opensearch'.", "location": {"path": "_ml-commons-plugin/gpu-acceleration.md", "range": {"start": {"line": 75, "column": 16}}}, "severity": "ERROR"}

[Service]
DevicePolicy=auto
```


After verifying that `nvidia-uvm` exists under `/dev`, you can start OpenSearch inside your cluster.

### Preparing AWS Inferentia ML node
Expand Down
Loading