Skip to content

grill-perf compare: A/B/A with noise floor, and ≥3-rep spread #14

Description

@plotarmordev

Problem

Two unchanged GLM runs (docs/performance/2026-09-09-recipe-smoke.md) differed 23–35% in achieved throughput; compare reported the change as eligible because outputs matched. With only two trials per cell there is no spread to judge against.

Evidence

A/A: single 33.8 → 25.9 tok/s, two-lane 70.0 → 45.7 tok/s, no deployment change. A later A/B/A for a scheduler flag needed the A1↔A2 drift (131 s vs 108 s) to interpret B (15 s).

Proposal

compare A B A2: treat A↔A2 as the noise floor; report B's change and mark it within_noise when |change| ≤ the A/A2 delta. Per cell, emit min/median/max and, with ≥3 trials, a bootstrap 95% CI on the median; withhold "change" when intervals overlap.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions