feat(perf): add flag-gated composite metric for serving KEEP decisions - #1316
Open
hmahmad26 wants to merge 2 commits into
Open
feat(perf): add flag-gated composite metric for serving KEEP decisions#1316hmahmad26 wants to merge 2 commits into
hmahmad26 wants to merge 2 commits into
Conversation
Co-authored-by: Cursor <cursoragent@cursor.com>
When the composite flag is on with a full triple, session totals, conc-sweep speedup, and the 10% roofline refresh step use S instead of output tok/s. Co-authored-by: Cursor <cursoragent@cursor.com>
hmahmad26
pushed a commit
to hmahmad26/Hyperloom
that referenced
this pull request
Sep 1, 2026
Local integration of PR AMD-AGI#1315 plus-sign JSON with PR AMD-AGI#1316 composite S.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
S = 0.55Δ_in + 0.30Δ_intv + 0.15Δ_out, withΔ_x = max(0, (x_cand - x_B) / x_B).HYPERLOOM_PERF_METRIC=composite_v1. Scriptable frameworks stay on output-throughput grading.HYPERLOOM_PERF_NOISE_PCT. Intvty p90 is a hard gate: a regression fails KEEP.Test plan
test_perf_metric.py(score, noise=0, intvty gate)test_map_aiperf.py(input tput / p90 tpot / intvty mapping)test_grid_runner.pyand related grid-runner unit filestest_benchmark_result.py,test_explore_executor.pyMade with Cursor