DisaggregatedSet

DisaggregatedSet is a Kubernetes controller and CRD (Custom Resource Definition) that extends LeaderWorkerSet (LWS) to support disaggregated inference workloads — use cases where different roles (e.g., prefill, decode, encode) need to run on separate, independently-scaled groups of pods.

This is especially useful for large language model (LLM) inference services where:

• The prefill role (generating the initial KV cache from the input prompt) is compute-bound and benefits from larger pod groups.
• The decode role (token-by-token autoregressive generation) is memory-bandwidth-bound and can run on smaller groups.
• The encode role (optional context encoding) may have different resource requirements from either.

DisaggregatedSet was introduced in KEP-766 to address these multi-role, multi-resource serving patterns with a single, declarative Kubernetes resource.

Relationship to LeaderWorkerSet

DisaggregatedSet does not replace LeaderWorkerSet — it orchestrates multiple LeaderWorkerSets.

Each role defined in a DisaggregatedSet spec maps to an independent LeaderWorkerSet, deployed in the same namespace. This means:

Child LeaderWorkerSets use a slice index and a revision hash in their names:

DisaggregatedSet "my-inference"
├── roles[0]: prefill  →  LeaderWorkerSet "my-inference-0-<rev>-prefill"
├── roles[1]: decode   →  LeaderWorkerSet "my-inference-0-<rev>-decode"
└── roles[2]: encode   →  LeaderWorkerSet "my-inference-0-<rev>-encode"

Naming format: <DisaggregatedSet-name>-<slice>-<revision-hash>-<role-name>. The revision hash is dynamic — always select child resources with labels (disaggregatedset.x-k8s.io/name, disaggregatedset.x-k8s.io/role, disaggregatedset.x-k8s.io/slice) rather than hardcoding names.

Each child LWS inherits standard LWS capabilities such as subgroup policies, exclusive placement, volume claim templates, and health monitoring. Rollout strategy for the set is owned by the DisaggregatedSet controller (see below).

Roles in DisaggregatedSet

A DisaggregatedSet spec contains a roles list. Each role defines:

DisaggregatedSet coordinates lifecycle and rollouts across roles. Each role’s replica count, rollout strategy, and pod template can be configured independently, while the controller manages them as a single cohesive unit.

Optional top-level fields such as slices (replicate the full role topology) and placementPolicy (topology co-location / spread) are covered in the examples and operations guide.

When to Use DisaggregatedSet vs Plain LWS

Use plain LWS when:

• All inference pods are homogeneous (same model, same resources).
• You do not need to separate prefill from decode.
• You are running training jobs or batch workloads without disaggregation.

Use DisaggregatedSet when:

• You are running disaggregated LLM inference (e.g., vLLM with P/D disaggregation, SGLang).
• Different inference phases require different GPU types or different pod group sizes.
• You want to scale prefill and decode replicas independently based on different traffic patterns.
• You are evaluating disaggregated serving architectures and need first-class Kubernetes support.

Key Design Principles

1. LWS-native — DisaggregatedSet is built on top of LWS, not alongside it. This means LWS features (failure handling, subgroup topology, exclusive placement) are available per role. Note: rollout strategy is owned by the DisaggregatedSet controller, which replaces the per-LWS rollout to coordinate updates across roles.

2. Coordinated rollouts — Rollouts across roles are coordinated by DisaggregatedSet to preserve capacity ratios (e.g., prefill-to-decode ratio) throughout the update process. Partition-based rollout is not supported.

3. Declarative — The entire multi-role inference topology is expressed in a single YAML manifest, making it easy to version-control and apply via GitOps.

Further Reading

• KEP-766: DisaggregatedSet design document
• Installation guide
• API Reference
• Labels and annotations
• Examples and operations
• In-repo samples: config/samples/disaggregatedset_v1_disaggregatedset.yaml, config/samples/disaggregatedset_v1_3role.yaml