Repository navigation
Keep planner costs tied to the configured global batch - #14
Merged
kaiwenKevinn merged 1 commit intoOct 20, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
GRP currently prices rollout work using its entire accumulated request history. Repeating the same sequence-length distribution can therefore increase the estimated cost of one fixed global batch and change resource decisions.
Normalize historical requests to a deterministic representative batch of
B_globalrequests before estimating current, searched, and forced layouts. Apply the same rule to direct optimizer calls, preserve the shortest and longest observed sequences, and keep the original history count in diagnostics.Adds six regression tests covering repeated and short histories, direct optimizer calls, forced layouts, and representative-batch edge cases. This change only affects planner cost estimation.
Validation (re-run on 2026-10-20):
scripts/test_cpu_ci.sh, including the new regressions: 86 passed.