prefix state temp fix - write state to both plugin state and cycle state #1509
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
Signed-off-by: Nir Rozenbaum <nirro@il.ibm.com>
✅ Deploy Preview for gateway-api-inference-extension ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: nirrozenbaum The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
k8s-ci-robot
added
the
cncf-cla: yes
k8s-ci-robot
added
approved
nirrozenbaum
changed the title
|
/lgtm |
k8s-ci-robot
added
the
lgtm
nirrozenbaum
added a commit
that referenced
this pull request
Sep 2, 2025
Signed-off-by: Nir Rozenbaum <nirro@il.ibm.com>
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Outdated suggestions cannot be applied.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 type of PR is this?
/kind bug
What this PR does / why we need it:
This PR adds back the writing of Prefix State to CycleState.
When switching to use
PluginStateinstead ofCycleStatein Prefix plugin, I forgot that PD profile handler in llm-d consumes the prefix state throughCycleStatevariable.This PR does a temporary fix to write the state to both
PluginStateandCycleStateand is only meant to solve the issue for llm-d release.once we release, I will work on a long term fix - exposing in
PluginStatethe fields that are needed by the plugin extension points, and exposing inCycleStatea different struct, that may be beneficial for other plugins, like sharing the hit percentage per endpoint (which is used by llm-d). This fix will also solve a different problem, where llm-d profile handler needs to access the prefix plugin block hash size in order to calculate the hit percentage (it's not the role of pd handler to calc the prefix hit percentage, it's prefix plugin role).Which issue(s) this PR fixes:
blocker for llm-d release
Does this PR introduce a user-facing change?:
cc: @kfswain @liu-cong