Add cache usage properties to ChatSampler and warning for cache overflow in prefill#578
Open
Ayushhgit wants to merge 3 commits intogoogle-deepmind:mainfrom
Open
Add cache usage properties to ChatSampler and warning for cache overflow in prefill#578Ayushhgit wants to merge 3 commits intogoogle-deepmind:mainfrom
Ayushhgit wants to merge 3 commits intogoogle-deepmind:mainfrom
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR improves cache observability and developer feedback in the sampling pipeline.
Changes:
cache_usedproperty toChatSamplerto expose the current number of tokens stored in the KV cache.cache_used_fracproperty (0.0–1.0) to indicate relative cache utilization._prefill.pywith alogging.warningthat triggers when the prompt length exceeds the configuredcache_length.Motivation:
These additions make it easier to monitor cache usage during long-running conversations and detect potential cache overflow before generation errors occur.
No functional behavior of sampling or prefill logic was modified.