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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
--calibratorand--calibrator-params.--taylorseer,--dmd,--foca) and algorithm-specific CLI flags/aliases (--taylorseer-order,-order/--order,--dmd-history,--dmd-svd-precision/--dmd-svd).perf.pyTaylorSeer default oforder=2; reject ambiguous--cache-config+ CLI calibrator combinations.Breaking changes
Scope notes
docs/papers/is intentionally unchanged in this task, sodocs/assets/dbprune.pngremains for its existing reference.devbranch also contains the previously committed 2026 cache-algorithm research documentation (1b30e998, related to [RFC] 2026 DiT Cache Algorithm Integration Research #1363).FLUX E2E performance and accuracy
Environment: FLUX.1-dev, 1024x1024, 28 steps, bf16, seed 0, one RTX PRO 5000 Blackwell. Timing is the single-run formal
Inference Time, excluding warmup/compile. PSNR/SSIM use the no-cache baseline as reference.The unified CLI was also exercised with
--calibrator taylorseer --calibrator-params order=2: E2E succeeded, loggedT1O2, hit 12/28 cache steps, and completed inference in 8.68s.Validation
--calibrator-params order=2;perf.pydefaultorder=2and conflict rejection verified.compileall, shell syntax checks,git diff --check, IDE diagnostics, and all pre-commit hooks passed.git merge-treeagainstorigin/main: clean.Downstream compatibility (static audit only)
Text and AST scans found no DBPrune usage in sglang, vllm-omni, xDiT, or TensorRT-LLM. vllm-omni and TensorRT-LLM summary call sites do not consume removed prune stats. No downstream repositories were modified and no downstream test suites were run.
Closes #1365.