Merged
Conversation
Signed-off-by: Michael Kalantar <kalantar@us.ibm.com>
Collaborator
Author
|
@maugustosilva fyi |
There was a problem hiding this comment.
Pull request overview
This PR aims to fix Helm chart rendering for multinode: true (LeaderWorkerSet) when initContainers are provided, which previously could produce an invalid Kubernetes manifest (Issue #241).
Changes:
- Adjusts
initContainersYAML indentation in the LeaderWorkerSet templates for bothdecodeandprefill. - Bumps the Helm chart version from
v0.4.8tov0.4.9. - Updates rendered example manifests to reflect the new chart version (and includes a small schema description tweak).
Reviewed changes
Copilot reviewed 15 out of 15 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| examples/output-xpu.yaml | Updates helm.sh/chart label to llm-d-modelservice-v0.4.9. |
| examples/output-xpu-pd.yaml | Updates helm.sh/chart label to llm-d-modelservice-v0.4.9. |
| examples/output-requester.yaml | Updates helm.sh/chart label to llm-d-modelservice-v0.4.9. |
| examples/output-pvc.yaml | Updates helm.sh/chart label to llm-d-modelservice-v0.4.9. |
| examples/output-pvc-hf.yaml | Updates helm.sh/chart label to llm-d-modelservice-v0.4.9. |
| examples/output-pd.yaml | Updates helm.sh/chart label to llm-d-modelservice-v0.4.9. |
| examples/output-pd-mnnvl.yaml | Updates helm.sh/chart label to llm-d-modelservice-v0.4.9. |
| examples/output-heterogeneous-pd.yaml | Updates helm.sh/chart label to llm-d-modelservice-v0.4.9. |
| examples/output-gaudi.yaml | Updates helm.sh/chart label to llm-d-modelservice-v0.4.9. |
| examples/output-dra.yaml | Updates helm.sh/chart label to llm-d-modelservice-v0.4.9. |
| examples/output-cpu.yaml | Updates helm.sh/chart label to llm-d-modelservice-v0.4.9. |
| charts/llm-d-modelservice/values.schema.json | Updates schema text for procMount description. |
| charts/llm-d-modelservice/templates/prefill-lws.yaml | Changes indentation for rendered prefill.initContainers in LWS. |
| charts/llm-d-modelservice/templates/decode-lws.yaml | Changes indentation for rendered decode.initContainers in LWS (alongside routing proxy init container). |
| charts/llm-d-modelservice/Chart.yaml | Bumps chart version to v0.4.9. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| {{- if .Values.prefill.initContainers }} | ||
| initContainers: | ||
| {{- toYaml .Values.prefill.initContainers | nindent 10 }} | ||
| {{- toYaml .Values.prefill.initContainers | nindent 8 }} |
Collaborator
There was a problem hiding this comment.
@copilot are you sure it's not supposed to indent 8?
jgchn
approved these changes
Mar 17, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fixes #241.