docs(perf): explain cache alignment and warmup limits - #18
Merged
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #17.
Explains why warmup alone may not yield a reported prefix hit: cache-block alignment and reuse are server-specific. Recommends inspecting reported counts and the engine's cache mechanism without promising that longer prompts guarantee a hit. Clarifies that switching to observe changes the workload and the claim, not the validity of a reported-hit run.
Documentation only; eligibility rules and existing workload bytes are unchanged. Reviewed by independent SIX and HELP as part of issue-slice review. Their source checks approved #17; no new inference-server call was made.