Feature/prophet kv#8
Open
almogtavor wants to merge 2 commits into
Open
Conversation
…mputation - Added query capturing functionality in the Attention layer to collect queries for ProphetKV. - Introduced new parameters in the AsyncScheduler and related classes to manage cached tokens and recompute requests. - Implemented gap recomputation logic in the Scheduler to handle virtual requests efficiently. - Enhanced NewRequestData to include cached token counts and support for gap recompute requests. - Updated ProphetKVGapPolicy to include new tunables for gap thresholds and maximum spans. - Refactored GPUModelRunner to support ProphetKV query collection and scoring, ensuring proper handling of cached tokens. - Improved error handling and logging for ProphetKV operations, including warnings for unsupported configurations.
almogtavor
pushed a commit
that referenced
this pull request
Jun 2, 2026
chore: remove spans redundant files
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Purpose
Test Plan
Test Result
Essential Elements of an Effective PR Description Checklist
supported_models.mdandexamplesfor a new model.