Integration with ONNX 1.19 - #25678
Merged
Ti-Tai Wang (titaiwangms) merged 37 commits intoSep 6, 2025
Merged
Ti-Tai Wang (titaiwangms) merged 37 commits into
Ti-Tai Wang (titaiwangms) merged 37 commits into
Conversation
Ti-Tai Wang (titaiwangms)
changed the title
Ti-Tai Wang (titaiwangms)
marked this pull request as ready for review
August 28, 2025 20:43
Ti-Tai Wang (titaiwangms)
requested review from
Changming Sun (snnn) and
Xavier Dupré (xadupre)
August 28, 2025 20:48
Ti-Tai Wang (titaiwangms)
added
the
dependencies
Contributor
Author
|
Need to fix |
Justin Chu (justinchuby)
previously approved these changes
Sep 3, 2025
Contributor
Author
|
Changming Sun (@snnn) Could you help me confirm whether these 4 CI failures are related or not (I think it's unrelated.). |
Contributor
|
Will check. Sorry, I was working on an ORT release. There were a lot of pipeline problems there. |
Contributor
Author
Can I directly merge this PR if it's only these failures? There would be more works to move them to a new branch under official repo. |
Justin Chu (justinchuby)
previously approved these changes
Sep 5, 2025
Justin Chu (justinchuby)
approved these changes
Sep 5, 2025
Ti-Tai Wang (titaiwangms)
merged commit Sep 6, 2025
ecb26fb
into
microsoft:main
97 of 103 checks passed
| @@ -1,2 +1,2 @@ | |||
| onnx==1.17.0 | |||
| onnx==1.18.0 | |||
Ti-Tai Wang (titaiwangms)
added a commit
to titaiwangms/onnxruntime
that referenced
this pull request
Jun 2, 2026
ONNX 1.22 re-registers Range with an opset-27 schema (adds stash_type attr, widens type constraints; signature unchanged: 3 scalar inputs -> 1-D output).
- gather_fusion.cc: add 27 to GatherToSlice Range version list {1,11}->{1,11,27}; add opset-27 GatherToSliceFusion test.
- embed_layer_norm_fusion.cc: add 27 to the two Range path matchers (parent_path_3/4) so the embedding fusion still matches opset-27 models.
- coreml/nnapi/vsinpu/webnn base_op_builder.h: bump default GetMaxSupportedOpSet 25->27, matching the lockstep convention of prior ONNX-integration PRs (microsoft#26579, microsoft#25678, microsoft#24449) so opset-27 nodes are not spuriously rejected.
qdq_util.cc / layout_transformation_potentially_added_ops.h / kernel_type_str_resolver_utils.cc were checked and need no change (none reference the opset-27 ops Range/CausalConvWithState/LinearAttention).
Agent-signed-off: Developer (0ede529c) [claude-opus-4.6 via copilot]
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Ti-Tai Wang (titaiwangms)
added a commit
to titaiwangms/onnxruntime
that referenced
this pull request
Jun 15, 2026
ONNX 1.22 re-registers Range with an opset-27 schema (adds stash_type attr, widens type constraints; signature unchanged: 3 scalar inputs -> 1-D output).
- gather_fusion.cc: add 27 to GatherToSlice Range version list {1,11}->{1,11,27}; add opset-27 GatherToSliceFusion test.
- embed_layer_norm_fusion.cc: add 27 to the two Range path matchers (parent_path_3/4) so the embedding fusion still matches opset-27 models.
- coreml/nnapi/vsinpu/webnn base_op_builder.h: bump default GetMaxSupportedOpSet 25->27, matching the lockstep convention of prior ONNX-integration PRs (microsoft#26579, microsoft#25678, microsoft#24449) so opset-27 nodes are not spuriously rejected.
qdq_util.cc / layout_transformation_potentially_added_ops.h / kernel_type_str_resolver_utils.cc were checked and need no change (none reference the opset-27 ops Range/CausalConvWithState/LinearAttention).
Agent-signed-off: Developer (0ede529c) [claude-opus-4.6 via copilot]
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
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
4 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.
Description
Update ONNX to v1.19.0
The major updates of ONNX: https://github.com/onnx/onnx/wiki/Logistics-for-ONNX-Release-1.19.0
Remaining Issues
nonpad_kv_seqlento op.Attentnio since opset24test_attention_4d_with_past_and_present_qk_matmul_bias_3d_mask_causalandtest_attention_4d_with_past_and_present_qk_matmul_bias_4d_mask_causalTensorScatterSwishml_dtypesreplacescustom_element_typesin ONNX Use ml_dtypes everywhere onnx/onnx#7089