-
Notifications
You must be signed in to change notification settings - Fork 316
Add openEuler Helm values for AudioQnA and CodeGen #2274
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.
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
base: main
Are you sure you want to change the base?
Conversation
Dependency Review✅ No vulnerabilities or license issues found.Scanned FilesNone |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This PR adds openEuler platform support for the AudioQnA Helm deployment by introducing a specialized values file. The configuration enables specific services compatible with openEuler while disabling others, and standardizes on openEuler-specific image tags.
- Adds
cpu-openeuler-value.yaml
with openEuler-specific service configurations - Enables
vllm
andspeecht5
services while disablingtgi
andgpt-sovits
- Configures all enabled services to use
latest-openeuler
image tags
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
image: | ||
tag: latest-openeuler | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The global latest-openeuler
tag may not apply to all services. Consider removing this global setting since individual services already specify their own tags explicitly (lines 17, 22, 29, 35).
image: | |
tag: latest-openeuler |
Copilot uses AI. Check for mistakes.
enabled: true | ||
image: | ||
repository: openeuler/vllm-cpu | ||
tag: 0.10.1-oe2403lts |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The vllm service uses a specific versioned tag 0.10.1-oe2403lts
while other services use latest-openeuler
. Consider using consistent tagging strategy across all services for better maintainability and predictable deployments.
tag: 0.10.1-oe2403lts | |
tag: latest-openeuler |
Copilot uses AI. Check for mistakes.
668c595
to
69d923c
Compare
Signed-off-by: zhihang <[email protected]>
5b5cbc5
to
1ff1c73
Compare
78dd724
to
1e27848
Compare
Signed-off-by: zhihang <[email protected]>
47841dd
to
27ce1d8
Compare
for more information, see https://pre-commit.ci
Description
This pull request introduces new Helm values files for deploying services on openEuler-based CPU images in both the
AudioQnA
andCodeGen
projects. The main goal is to override image tags and repositories to ensure compatibility with openEuler, and to selectively enable or disable services based on the deployment needs.Helm values for openEuler compatibility:
cpu-openeuler-values.yaml
toAudioQnA/kubernetes/helm
, setting image tags tolatest-openeuler
and updating repositories for services likevllm
, while enabling/disabling services as appropriate.cpu-openeuler-values.yaml
toCodeGen/kubernetes/helm
, overriding image tags and repositories for all enabled services to use openEuler-compatible images, and configuring backend settings for text generation and embeddings.cpu-tgi-openeuler-values.yaml
toCodeGen/kubernetes/helm
, specifically enabling the TGI service with openEuler images and disabling VLLM, while updating other service images and backend settings for openEuler compatibility.Issues
#2264
Type of change
List the type of change like below. Please delete options that are not relevant.
Dependencies
List the newly introduced 3rd party dependency if exists.
Tests
Describe the tests that you ran to verify your changes.