Skip to content

Conversation

@capri-xiyue
Copy link
Contributor

@capri-xiyue capri-xiyue commented Jan 7, 2026

What type of PR is this?

/kind feature
What this PR does / why we need it:
Refactor epp to be its standalone helm chart and inferencePool be its parent chart. I followed the helm practise https://helm.sh/docs/chart_template_guide/subcharts_and_globals/ here.
See #2063
Which issue(s) this PR fixes:

Fixes #2063

Does this PR introduce a user-facing change?:

When installing `inferencePool` helm chart, 

**Old Values Key:**
`inferencePool.xxx`, `provider.xxx`, `inferenceExtension.xxx`

**New Values Key:**
`global.inferencePool.xxx`, `global.provider.xxx`, `epp.inferenceExtension.xxx`

Example is as follows:
--set inferencePool.modelServerType=vllm \
--set provider.name=gke \
--set inferenceExtension.replicas=1

will change to

--set global.inferencePool.modelServerType=vllm \
--set global.provider.name=gke \
--set epp.inferenceExtension.replicas=1

@k8s-ci-robot k8s-ci-robot added the do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress. label Jan 7, 2026
@netlify
Copy link

netlify bot commented Jan 7, 2026

Deploy Preview for gateway-api-inference-extension ready!

Name Link
🔨 Latest commit d624ddb
🔍 Latest deploy log https://app.netlify.com/projects/gateway-api-inference-extension/deploys/695edab6c243d00008633d56
😎 Deploy Preview https://deploy-preview-2089--gateway-api-inference-extension.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify project configuration.

@k8s-ci-robot
Copy link
Contributor

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: capri-xiyue
Once this PR has been reviewed and has the lgtm label, please assign ahg-g for approval. For more information see the Code Review Process.

The full list of commands accepted by this bot can be found here.

Details Needs approval from an approver in each of these files:

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@k8s-ci-robot k8s-ci-robot added size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files. cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. labels Jan 7, 2026
@capri-xiyue
Copy link
Contributor Author

capri-xiyue commented Jan 7, 2026

I sent this early so that @LukeAVanDrie can check why the pod locator break the epp standalone logic.
Reviewers don't need to review it

@capri-xiyue
Copy link
Contributor Author

/unblock

@capri-xiyue
Copy link
Contributor Author

/unhold

@capri-xiyue capri-xiyue changed the title WIP: helm refactor feature: Change epp to be its standalone helm chart and inferencePool be its parent chart Jan 7, 2026
@k8s-ci-robot k8s-ci-robot removed the do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress. label Jan 7, 2026
@capri-xiyue capri-xiyue changed the title feature: Change epp to be its standalone helm chart and inferencePool be its parent chart feat: Change epp to be its standalone helm chart and inferencePool be its parent chart Jan 7, 2026
@capri-xiyue
Copy link
Contributor Author

@ahg-g @kfswain
This PR is ready for review.
To avoid the duplicate code, I decided to follow https://helm.sh/docs/chart_template_guide/subcharts_and_globals/ to make epp a subchart of inferencePool and at the same time epp can be installed alone.

This change brought some break changes when users install inferencePool, I've included the details of break changes in the release note of the PR. Let me know whether such break change is allowed or not.

@capri-xiyue
Copy link
Contributor Author

/assign @ahg-g

@capri-xiyue
Copy link
Contributor Author

/assign @kfswain

@k8s-ci-robot
Copy link
Contributor

PR needs rebase.

Details

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository.

@k8s-ci-robot k8s-ci-robot added the needs-rebase Indicates a PR cannot be merged because it has merge conflicts with HEAD. label Jan 9, 2026
@ahg-g
Copy link
Contributor

ahg-g commented Jan 9, 2026

This refactor is not backward compatible, it will break existing guides as well as llm-d charts that import the infPool one

@capri-xiyue
Copy link
Contributor Author

This refactor is not backward compatible, it will break existing guides as well as llm-d charts that import the infPool one

Discussed offline, helm suggested approach global introduces break change.

I will investigate other hacky ways to shared values without global at the cost that conflict naming may cause weird issues.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. needs-rebase Indicates a PR cannot be merged because it has merge conflicts with HEAD. size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[Standalone] refactor epp outside of existing inference pool helm chart

4 participants