Repository navigation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add BeziCast (arXiv:2610.16448) as an experimental DBCache calibrator for non-uniform historical anchors.
Related to #1363.
What changed
BeziCastCalibratorwith a FIFO of up to six real full-compute anchors, Bernstein equivalent weights, and Tikhonov stabilization.K=6,n=4, andridge=0.5; usepinvfor exact zero-ridge interpolation.rho=auto, query clipping, explicit insufficient-anchor reuse, and observable counters for forecasts, warmup reuse, numerical fallback, clipping, and guardrail blending.--calibrator bezicast --calibrator-params history=6,control_points=4,ridge=0.5,guardrail=false.DBCache scheduling, Fn/Bn granularity, warmup, and cache guards are unchanged.
Tests
FLUX.1-dev E2E
Environment: RTX PRO 5000, physical GPU 2, torch 2.15.0+cu132, 1024x1024, 28 steps, seed 0. Every cache arm reports 12/28 Cache Steps; neither BeziCast arm emits a numerical-fallback warning.
Repeat / noise floor
This is a single-prompt compile wiring probe, not a universal predictor ranking. The first-run guardrail on/off difference is about 0.10dB and is not evidence of a gain; guardrail-on also has a worse same-config repeat floor, so it remains opt-in.
Visual comparison
All outputs preserve the cat, sign, and
Hello worldtext; no black images or structural corruption were observed.