CoreML: Add support for Pad with 'reflect' for ML Program#28073
Merged
skottmckay merged 16 commits intomainfrom Apr 20, 2026
Merged
CoreML: Add support for Pad with 'reflect' for ML Program#28073skottmckay merged 16 commits intomainfrom
skottmckay merged 16 commits intomainfrom
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Adds CoreML EP (ML Program) support for Pad with mode="reflect" and introduces regression coverage around CoreML model loading/padding behavior.
Changes:
- Enable Pad op builder support for ML Program and implement MIL
padop wiring forconstant/reflect. - Tighten/adjust Pad support checks (mode gating, reflect constraints).
- Add a new CoreML EP test covering
Pad(mode=reflect)with ML Program.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 4 comments.
| File | Description |
|---|---|
| onnxruntime/test/providers/coreml/coreml_basic_test.cc | Adds a new ML Program Pad(mode=reflect) regression test alongside existing CoreML tests. |
| onnxruntime/core/providers/coreml/builders/impl/pad_op_builder.cc | Implements ML Program path for Pad (including reflect) and updates support checks/initializer skipping. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
…ssion test Agent-Logs-Url: https://github.com/microsoft/onnxruntime/sessions/93f6c70a-6288-4790-a265-f95f6f793843 Co-authored-by: skottmckay <979079+skottmckay@users.noreply.github.com>
Agent-Logs-Url: https://github.com/microsoft/onnxruntime/sessions/93f6c70a-6288-4790-a265-f95f6f793843 Co-authored-by: skottmckay <979079+skottmckay@users.noreply.github.com>
Agent-Logs-Url: https://github.com/microsoft/onnxruntime/sessions/93f6c70a-6288-4790-a265-f95f6f793843 Co-authored-by: skottmckay <979079+skottmckay@users.noreply.github.com>
Contributor
Author
|
/azp run Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Linux QNN CI Pipeline |
|
Azure Pipelines successfully started running 4 pipeline(s). |
Contributor
Author
|
/azp run Windows GPU Doc Gen CI Pipeline |
|
Azure Pipelines successfully started running 1 pipeline(s). |
Contributor
Author
|
@copilot resolve the merge conflicts in this pull request |
# Conflicts: # onnxruntime/test/providers/coreml/coreml_basic_test.cc Co-authored-by: skottmckay <979079+skottmckay@users.noreply.github.com>
Contributor
Resolved in b6e58ca by merging latest |
Contributor
Author
|
/azp run Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline,Linux QNN CI Pipeline |
|
Azure Pipelines successfully started running 3 pipeline(s). |
edgchen1
reviewed
Apr 18, 2026
…xruntime into skottmckay/GH28022
…han two dimensions only supports constant mode"
edgchen1
approved these changes
Apr 20, 2026
Contributor
|
Verified this works for me in my application. Thanks a lot! :) |
maxwbuckley
added a commit
to maxwbuckley/Deep-Live-Cam
that referenced
this pull request
Apr 22, 2026
…uting Bundles CoreML graph rewrites, GPU-accelerated pipeline work, Windows CUDA fixes, and Mac/Windows runtime routing into a single drop. CoreML (Apple Silicon): - Decompose Pad(reflect) → Slice+Concat in inswapper_128 so the model runs in one CoreML partition instead of 14 (TEMPORARY: fixed upstream in microsoft/onnxruntime#28073, drop when ORT >= 1.26.0). - Fold Shape/Gather chains to constants in det_10g (21ms → 4ms). - Decompose Split(axis=1) → Slice pairs in GFPGAN (155ms → 89ms). - Route detection model to GPU so the ANE is free for the swap model. - Centralize provider/config selection in create_onnx_session. Pipeline (all platforms): - Parallelize face landmark + recognition post-detection; skip landmark_2d_106 when only face_swapper is active. - Pipeline face detection with swap for ANE overlap. - GPU-accelerated paste_back, MJPEG capture, zero-copy display path. - Standalone pipeline benchmark script. Windows / CUDA: - CUDA graphs + FP16 model + all-GPU pipeline for 1080p 60 FPS. - Auto-detect GPU provider and fix DLL discovery for Windows CUDA execution. Cross-platform: - platform_info helper for Mac/Windows runtime routing. - GFPGAN 30 fps + MSMF camera 60 fps with adaptive pipeline tuning. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
9 tasks
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.
Description
Add support for 'reflect' if ML Program is enabled. Uses the CoreML implementation directly.
Motivation and Context
#28022