Repository navigation
perf: reuse completed rendering during assistant boundary checks - #985
Draft
bradhilton wants to merge 2 commits into
Draft
bradhilton wants to merge 2 commits into
bradhilton wants to merge 2 commits into
Conversation
bradhilton
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Agent: Hayek
Assistant boundary checks can render the same completed history twice. Reuse the completed rendering when the messages and generation flag match; changed prefixes still require their own boundary proof.
Validation: 80 checks passed. Seven paired public CPU measurements improved from 429.60 to 418.19 ms while preserving tokens, flags, logprobs, and masks. The gain is modest and repeated prefix rendering remains the main cost.
Stacked on #977. This is fixture evidence, not retained 062 acceptance or a live throughput result.