Add VAE graph optimization surgeries - #1260
Draft
xieofxie wants to merge 7 commits into
Draft
Conversation
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| from typing import Any, ClassVar | ||
|
|
||
| import numpy as np | ||
| import onnx |
| dimensions.append(dimension.dim_param) | ||
| else: | ||
| dimensions.append(None) | ||
| shapes[value.name] = tuple(dimensions) |
| from typing import TYPE_CHECKING | ||
|
|
||
| import numpy as np | ||
| import onnx |
added 3 commits
July 31, 2026 14:40
…_to_optimize # Conflicts: # src/winml/modelkit/commands/optimize.py # src/winml/modelkit/optim/analysis.py # tests/unit/commands/test_optimize_cli.py # tests/unit/optim/test_analysis.py
…e' into hualxie/more_optims_vae_draft
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
GatherNDpaths, exact SiLU topology, and scaledMatMulQuickGeluafterward so contrib operators survive the full pipelinevae_opt.mdBehavior
All new capabilities are disabled by default.
QuickGeluandFusedMatMulare constrained to CUDA. The scaledMatMulrewrite is algebraically equivalent but may change floating-point rounding when scaling is incorporated into GEMM.