docs: Add documentation for LLMInferenceService label and annotation propagation
- Dominant language
- MDX
- Stars
- 113
- Forks
- 193
- Avg merge
- 5d 20h
- Merged PRs (30d)
- 3
Description
**Describe the change you'd like to see**
Add a documentation page for the LLMInferenceService label and annotation propagation feature, as requested by @sivanantha321 in kserve/kserve#5009 (https://github.com/kserve/kserve/pull/5009#issuecomment-3989171200).
This feature (merged in kserve/kserve#5009) enables users to propagate Kubernetes labels and annotations from an `LLMInferenceService` resource to the workload pods it manages. It supports all deployment modes: single-node Deployments, multi-node LeaderWorkerSets, disaggregated prefill-decode workloads, and the scheduler (EPP) Deployment.
The documentation should cover:
- **Two propagation layers**: top-level metadata (prefix-filtered via an approved allowlist) vs. spec-level fields (`spec.labels`, `spec.annotations`, and per-component equivalents) which propagate all keys without filtering.
- **Approved prefix allowlists**: which annotation prefixes (`k8s.v1.cni.cncf.io`, `kueue.x-k8s.io`, `prometheus.io`) and label prefixes (`kueue.x-k8s.io`) are propagated from `.metadata`.
- **Per-component spec fields**: `spec.prefill.labels`/`spec.prefill.annotations` for prefill pods and `spec.router.scheduler.labels`/`spec.router.scheduler.annotations` for the scheduler pod.
- **Multi-node behaviour**: propagation to both leader and worker pod templates.
- **Precedence rules**: spec-level values override top-level metadata when the same key appears in both.
- **Practical examples**: Kueue queue assignment, Multus CNI attachment, Prometheus scraping config, and custom platform labels for cost allocation.
Suggested location: `docs/model-serving/generative-inference/llmisvc/llmisvc-label-propagation.md` under the existing LLMInferenceService sidebar category.
**Additional context**
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with the merged kserve/kserve#5009 change and the existing LLMInferenceService sidebar category. Add docs/model-serving/generative-inference/llmisvc/llmisvc-label-propagation.md covering propagation layers, approved prefixes, component fields, multi-node behavior, precedence, and the requested Kueue, Multus, Prometheus, and cost-allocation examples. Done means the page documents all listed deployment modes and practical examples.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- kubernetes
- Domain
- documentation
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- Half a day
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 55/100