Repository navigation
Complete opset 28 Optional runtime type integration - #32393
Merged
Justin Chu (justinchuby) merged 12 commits intoOct 26, 2026
Merged
Justin Chu (justinchuby) merged 12 commits into
Justin Chu (justinchuby) merged 12 commits into
Conversation
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Register complex and FP6 tensor, sequence, and optional runtime types across IR14 kernel constraints and the shared-provider bridge. Add focused type-info and CPU Optional opset-28 coverage while preserving pre-28 boundaries. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 4b3f49bc-2c29-4f73-9bcb-789e6b0e67d5
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 4b3f49bc-2c29-4f73-9bcb-789e6b0e67d5
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 4b3f49bc-2c29-4f73-9bcb-789e6b0e67d5
Avoid passing template commas directly through GTest assertion macros so the focused type-info coverage compiles on MSVC. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 4b3f49bc-2c29-4f73-9bcb-789e6b0e67d5
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 4b3f49bc-2c29-4f73-9bcb-789e6b0e67d5
Member
|
Why do we need complex? They are never used. |
Contributor
Author
|
Good point. Removing |
Keep opset 28 Optional focused on FP6 and other registered IR14 types while removing complex registrations and provider bridge ABI additions. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Preserve opset 28 Optional registrations alongside new Cast, QDQ, and BitShift kernels. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Ti-Tai Wang (titaiwangms)
pushed a commit
that referenced
this pull request
Oct 12, 2026
### Description <!-- Describe your changes. --> Reintegrate the ONNX 1.23 base plumbing originally introduced by #32359 and reverted by #33073, now using ONNX **1.23.2**. - Coordinate source/submodule, FetchContent, vcpkg, and Python dependency pins and raise the relevant opset ceilings to 28. - Restore Float6 public element-type mappings and conversion coverage, preserving subsequent independent type-support changes. - Update existing-type Cast registrations, CPU/CUDA Mod boundaries, signed BitShift support, provider compatibility, backend filters/tolerances, and operator documentation. - Materialize the removed upstream node-test corpus with exact-version and minimum-case guards, and cover backend serialization and released-opset policy. - Keep matching FetchContent/vcpkg compatibility patches; remove the released-opset correction now fixed upstream in 1.23.2. - Address review feedback: OpenVINO rejects BitShift-28; CPU/CUDA legacy SpaceToDepth kernels stop at 27; DirectML accepts only safe DCR; unverified graph providers defer SpaceToDepth-28. Full builds use ONNX function expansion for CRD, with literal-output and routing regressions. Avoid creating unsupported SpaceToDepth-28 nodes in the post-expansion Slice/Concat fusion. - Use shared ABI-safe tensor-element conversion in the native ONNX node runner, fixing INT2/UINT2/FLOAT8E8M0 corpus decoding after the main merge. ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> This is a redo of #32359 after its rollback in #33073. ONNX 1.23.2 includes the external tensor read/re-save fix from onnx/onnx#8472 for onnx/onnx#8471 and the released-opset metadata fix from onnx/onnx#8544 for onnx/onnx#8529. The redundant local `LastReleaseVersionMap` patch has been removed. Remaining FetchContent/vcpkg patches are byte-identical and apply against the pinned release. **Scope:** This PR establishes dependency/runtime base integration. Full per-operator opset-28 support remains separate follow-up work; see #32362, #32369, #32372, #32378, #32381, and #32393. These references describe staged scope, not a claim that every follow-up has landed or every opset-28 operator is supported. Runtime function expansion is a full-build fallback, not minimal/ORT-format runtime coverage. ### Local validation Completed on Windows with retained CPU-only Ninja/MSVC `RelWithDebInfo` builds and strict released-opset policy: - Built `onnxruntime_provider_test`, `onnxruntime_test_all`, `onnx_test_runner`, and Python bindings against ONNX 1.23.2; retained build remains available for incremental work. - Source-built and installed the exact patched ONNX 1.23.2 Python wheel. - Separate `--minimal_build extended` shared runtime configured, compiled, and linked successfully with ML/contrib ops and unit tests disabled. This exercises `ONNX_MINIMAL_BUILD=ON`; it is not a minimal-runtime function-op execution test. - Mod/BitShift/SpaceToDepth/Cast provider tests: **247 passed**, no skips. SpaceToDepth checks default DCR, explicit DCR, and CRD with distinct literal expected outputs, expansion, and legacy opset boundaries. - Slice/Concat fusion and type-info/tensor-proto framework tests: **27 passed**, no skips. - Python backend tests: **22 passed**, plus **2 subtests passed**. - Full Python backend series: **4,066 tests**, **2,685 skipped**, zero failures. Skipped/unsupported coverage is not a pass. - Materialized **1,884 node cases**. Native CPU runner with `-m 1500` collected **1,760 cases**: **1,590 succeeded**, **170 not implemented**, **zero failed**, exit 0. These results do not establish complete opset-28 support. - Generated CPU operator documentation matches the rebuilt kernel registry; verified archive hashes, patch identity/application, submodule SHA, and changed-file lint. **Remaining validation/infrastructure limits:** GPU and other EP execution relies on CI; optional-provider routing checks are compiled into the relevant builds but were unavailable locally. Full unfiltered C++ suites and the ancillary broad `ALL` target were not rerun. The oracle-dependent corpus equivalence test skips because upstream no longer ships the corpus. The new ONNX 1.23.2 tarball currently returns **404 from the Microsoft vcpkg asset mirror**; it still needs Terrapin/infra seeding before read-only `x-block-origin` vcpkg legs can download it. FetchContent and the successful minimal build are mirror-independent. New-head CI is pending. --------- Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: gramalingam <10075881+gramalingam@users.noreply.github.com>
Preserve Optional opset 28 kernels and tests alongside the updated ONNX 1.23 base. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Contributor
|
Copilot resolve the merge conflicts in this pull request |
…ustinchuby-complete-optional-opset-28 # Conflicts: # onnxruntime/test/framework/type_info_test.cc Co-authored-by: gramalingam <10075881+gramalingam@users.noreply.github.com>
Contributor
|
Copilot resolve the merge conflicts in this pull request |
Contributor
Merged |
…ustinchuby-complete-optional-opset-28 Co-authored-by: gramalingam <10075881+gramalingam@users.noreply.github.com>
Contributor
Merged the latest |
Contributor
There was a problem hiding this comment.
🟡 Changes recommended
Complex runtime types remain unregistered, and Float4 tensor sequences fail type inspection.
2 open findings
What changed in this PR
Extends CPU Optional operators for opset 28 and introduces IR14 runtime type plumbing.
Changes:
- Adds IR14 tensor, sequence, and optional type collections.
- Splits CPU Optional kernel registrations at opset 28.
- Extends provider bridge APIs and adds focused tests.
| File | Description |
|---|---|
onnxruntime/test/providers/cpu/optional/optional_ops_test.cc |
Adds opset-28 FP6 Optional tests. |
onnxruntime/test/framework/type_info_test.cc |
Tests IR14 type registration and C API mappings. |
onnxruntime/core/session/provider_bridge_ort.cc |
Implements IR14 provider-host methods. |
onnxruntime/core/providers/shared_library/provider_wrappedtypes.h |
Exposes IR14 type lists to shared providers. |
onnxruntime/core/providers/shared_library/provider_interfaces.h |
Appends IR14 provider-host ABI methods. |
onnxruntime/core/providers/cpu/optional/optional_ops.cc |
Adds opset-28 Optional kernel constraints. |
onnxruntime/core/providers/cpu/cpu_execution_provider.cc |
Registers new Optional kernel versions. |
onnxruntime/core/framework/tensor_type_and_shape.cc |
Maps complex types to C API enums. |
onnxruntime/core/framework/data_types.cc |
Registers aggregate runtime types. |
include/onnxruntime/core/framework/data_types.h |
Declares IR14 type-list APIs. |
🧠 Review effort: Balanced
💡 Configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
Justin Chu (justinchuby)
deleted the
justinchuby-complete-optional-opset-28
branch
October 26, 2026 18:24
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
Stacked on #32372.
Motivation and Context
ONNX opset 28 expands Optional schemas to the IR14 tensor and sequence type sets. ORT needs matching runtime registration, TypeProto/public C API mappings, kernel constraints, and shared-provider access so valid complex and FP6 Optional values resolve consistently.
Local validation:
lintrunnerpassed for all 13 files in this stacked diffonnxruntime_frameworkrebuilt successfully after the additive FP6 base repair;tensorprotoutils.ccrecompiled and C2912 is gonedata_types.cc,tensor_type_and_shape.cc,cpu_execution_provider.cc,optional_ops.cc, andprovider_bridge_ort.ccoptional_ops_test.cc,type_info_test.cc, and the repaired FP6cast_op_test.cconnxruntime_provider_testandonnxruntime_test_allfail to link on 62 inherited opset-25/28 symbols (including Q/DQ/Cast kernel registrations, ONNX DepthToSpace/SpaceToDepth doc symbols, and Float4 aggregate types); no Optional symbol is among the unresolved references