[CRD] Add KVCachePool API and runtime connector specs#607
Open
YouNeedCryDear wants to merge 3 commits into
Open
[CRD] Add KVCachePool API and runtime connector specs#607YouNeedCryDear wants to merge 3 commits into
YouNeedCryDear wants to merge 3 commits into
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What this PR does
KVCachePoolAPI for provider-neutral KV cache pool configuration.InferenceService.spec.kvCachePoolas a reference-only binding to an existing pool.ServingRuntime.spec.kvCacheConnectorsfor runtime-side KV cache connector metadata.Why we need it
OME needs a first-class API for independently managed KV cache pools so serving endpoints can attach to compatible pool implementations without treating KV cache infrastructure as an
InferenceService-owned component. Runtime connector metadata lets the selected runtime describe how engine, decoder, router, or predictor components should connect to a referenced pool.Fixes #
How to test
Not run by Codex while creating this PR; the branch and commits were already pushed.
Checklist
make testpasses locally