Fix tps-utilization to normalize per pareto curve, not submission-wide - #63
Merged
Merged
Conversation
The §8.1 tps-utilization check computed a single submission-wide max system_tps and divided every run by it. When a submission contains more than one system (e.g. an MI355X 1x config alongside an 8x config), the smaller system's points were divided by the larger system's peak and could never match their stored (per-curve) values. Group run_metadata.json by its pareto curve (<system_desc_id>/<benchmark_model>) and normalize within each curve. Adds regression tests for the multi-system case and per-curve error detection. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
tanvi-mlcommons
approved these changes
Jul 13, 2026
|
MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅ |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The §8.1 tps-utilization check computed a single submission-wide max system_tps and divided every run by it. When a submission contains more than one system (e.g. an MI355X 1x config alongside an 8x config), the smaller system's points were divided by the larger system's peak and could never match their stored (per-curve) values.
Group run_metadata.json by its pareto curve (<system_desc_id>/<benchmark_model>) and normalize within each curve. Adds regression tests for the multi-system case and per-curve error detection.
Co-Authored: Claude