Repository navigation
Fix third-order DPM++ multistep coefficients - #15057
Draft
Robertboy18 wants to merge 1 commit into
Draft
Robertboy18 wants to merge 1 commit into
Robertboy18 wants to merge 1 commit into
Conversation
github-actions
Bot
added
tests
schedulers
fixes-issue
size/M
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #15056.
The third-order multistep update uses
D2as the quadratic coefficient, but its deterministic multiplier is missing a factor of two and its SDE multiplier has the wrong factor and sign. This corrects both, stabilizes the quadratic multiplier for small steps, and synchronizes the inverse scheduler copy.Independent polynomial-integral tests, float32/float64 small-step checks, and cubic-forcing refinement cover the change. The forward and inverse solver suites pass: 86 passed, 1 pre-existing skip. All seven new regression cases fail on the original implementation. Changed-file Ruff and copy consistency checks pass.
The SDE accuracy checks cover the drift of a state-independent scalar predictor. GPU behavior, image quality, and general stochastic convergence have not been tested.
AI-assisted implementation and tests; opening as a draft for author review.