Repository navigation
Conversation
Contributor
Author
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PlainPagedKVCacheAuxDataManagerreuses the same device arrays for global and per-layer sliding attention. Preparing the sliding page table therefore overwrites the global one before either layer uses it. In Gemma 4, a global layer then attends to only the sliding window and loses the earlier context.Give the plain manager separate storage for the sliding page indptr, page indices and length info, and select it at the per-layer sliding copy calls. Allocate it only when the cache has sliding layers. The cached manager already assigns each copy its own region.