Skip to content

doc: add doc best-practice/using-role-templates#387

Open
diw-zw wants to merge 2 commits into
sgl-project:mainfrom
diw-zw:0710-doc-02
Open

doc: add doc best-practice/using-role-templates#387
diw-zw wants to merge 2 commits into
sgl-project:mainfrom
diw-zw:0710-doc-02

Conversation

@diw-zw

@diw-zw diw-zw commented Jul 10, 2026

Copy link
Copy Markdown
Collaborator

No description provided.

@gemini-code-assist

Copy link
Copy Markdown

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

@cheyang

cheyang commented Jul 13, 2026

Copy link
Copy Markdown
Collaborator

/copilot review

@cheyang

cheyang commented Jul 13, 2026

Copy link
Copy Markdown
Collaborator

@gemini-code-assist /review

@gemini-code-assist

Copy link
Copy Markdown

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

@cheyang

cheyang commented Jul 13, 2026

Copy link
Copy Markdown
Collaborator

Well-structured documentation covering roleTemplates, templateRef, patch overrides, and leaderWorkerPattern integration. One factual error needs fixing: in both EN and ZH guide docs, the 'Patch Merge Rules' verification step shows expected output of 8Gi where it should be 16Gi (the whole point of that step is demonstrating the patch override). The surrounding text already correctly states 16Gi, so only the inline expected-output line needs updating.

# Verify Prefill Pod memory request is 16Gi (overridden by patch)
kubectl get pods -l rbg.workloads.x-k8s.io/role-name=prefill -o jsonpath='{.items[0].spec.containers[0].resources.requests.memory}'

> 8Gi

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This expected output contradicts the surrounding text. The comment on line 360 says "Verify Prefill Pod memory request is 16Gi (overridden by patch)" and the summary on line 382 says "Prefill memory: 16Gi", but this line shows > 8Gi. Should be > 16Gi.

# 验证 Prefill Pod 内存请求为 16Gi(被 patch 覆盖)
kubectl get pods -l rbg.workloads.x-k8s.io/role-name=prefill -o jsonpath='{.items[0].spec.containers[0].resources.requests.memory}'

> 8Gi

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Same issue here: the comment says memory should be 16Gi (overridden by patch), but the expected output shows > 8Gi. Should be > 16Gi.

kubectl get rbg <rbg-name> -o yaml | grep templateRef
```

## Related Documents

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nit: the 'Related Documents' section links to 01-deploy-inference-service.md, 08-configuring-autoscaling.md, and 03-configuring-rolling-updates.md which don't exist on the target branch yet. Also 'Gang Scheduling Configuration' has no link. Fine to leave as placeholders if follow-up PRs will add these.

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants