Add LLMInferenceService support - #5
Merged
Merged
Conversation
- minimal hand-written CRD type with spec.replicas and serde flatten - label fast-path: app.kubernetes.io/part-of=llminferenceservice - owner-ref chain: Pod -> RS -> Deployment -> LLMInferenceService - scale patches both spec.replicas and spec.prefill.replicas to zero - new 'l' flag in enabled-resources (default "drsinl") - 10 unit tests covering bitflags, conversion, equality, hashing, meta
A LeaderWorkerSet created by an LLMInferenceService now resolves to the owning LLMInferenceService: scaling the LWS alone is undone by the KServe controller reconciling it back. find_owner/get_typed helpers replace the nested owner-ref loops, From impls give every workload type a ScaleKind conversion, and with_kind_api! collapses the seven-arm fetch/patch matches. CRD schemas for the opaque passthrough fields now carry an explicit object type with x-kubernetes-preserve-unknown-fields so LeaderWorkerSet and LLMInferenceService CRDs install cleanly; kind e2e tests cover the LWS and LLMISVC-owned-LWS owner chains.
wseaton
force-pushed
the
feat/llminferenceservice-support
branch
from
August 31, 2026 12:44
c2ba4f3 to
ed11ce7
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds
serving.kserve.io/v1alpha1 LLMInferenceServiceas a scalable resource kind (lflag).resources::llminferenceserviceCRD definitionminReplicas: 0