Address edge GetMemInfo edge cases #26021

yuslepukhin · 2025-09-12T02:45:03Z

Description

This fixes somewhat contrived edgecases that are present in our tests

input propagates to output
output is produced by an initializer.

Motivation and Context

Python API upcoming PR does not pass tests without it.

- input propagates to output - output is produced by an initialier.

Copilot

Pull Request Overview

This PR addresses edge cases in the GetMemInfo functionality related to model inputs and outputs in contrived test scenarios. It fixes issues where input values propagate directly to outputs and where outputs are produced by constant initializers.

Enhanced memory info retrieval logic to handle edge cases in input/output relationships
Added comprehensive error handling for outputs produced by initializers or direct input propagation
Added null checks to prevent API calls when input/output counts are zero

Reviewed Changes

Copilot reviewed 3 out of 4 changed files in this pull request and generated 2 comments.

File	Description
onnxruntime/test/shared_lib/test_inference.cc	Added tests for input pass-through and sparse output scenarios
onnxruntime/core/session/inference_session.cc	Enhanced GetInputOutputMemoryInfo with fallback logic for edge cases
include/onnxruntime/core/session/onnxruntime_cxx_inline.h	Added null checks before API calls in memory info methods

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

onnxruntime/core/session/inference_session.cc

include/onnxruntime/core/session/onnxruntime_cxx_inline.h

onnxruntime/core/session/inference_session.cc

onnxruntime/test/testdata/input_propagated_to_output.onnx

onnxruntime/test/testdata/test_dangling_input_segment_ids.py

skottmckay

onnxruntime/test/testdata/test_dangling_input_segment_ids.py

+import sys
+
+import numpy as np
+import onnx


To fix the problem, remove the line from onnx import TensorProto, helper, numpy_helper (line 12) and replace all occurrences of TensorProto, helper, and numpy_helper with onnx.TensorProto, onnx.helper, and onnx.numpy_helper respectively, throughout the code snippet. This ensures code clarity and avoids confusion as recommended, and no APIs should change. The only file to be changed is onnxruntime/test/testdata/test_dangling_input_segment_ids.py. No new imports or definitions are needed, just refactoring for proper qualification.

### Description  This pull request introduces several enhancements to ONNX Runtime's Python and C++ APIs, focusing on improved device and memory information handling, synchronization stream support, and tensor copy functionality. It adds new Python bindings for device/memory types, exposes more detailed session input/output metadata, and provides a Python-accessible tensor copy API. The changes also refactor and extend the C++ API for better stream and memory info management. Key changes include: ### Device and Memory Information Enhancements * Added Python bindings for `OrtMemoryInfoDeviceType`, `OrtDeviceMemoryType`, and expanded `OrtDevice` to expose the memory type via a new `mem_type` method. The `OrtMemoryInfo` Python class now supports both legacy and new V2 constructors and exposes additional properties such as device memory type and vendor ID. [[1]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR1801-R1810) [[2]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR1839) [[3]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eL1941-R2005) * Extended the Python `InferenceSession` object to provide access to input/output `OrtMemoryInfo` and `OrtEpDevice` objects through new properties and methods. [[1]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR2702-R2729) [[2]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR202-R213) [[3]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR591-R593) [[4]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR607-R609) ### Synchronization Stream and Execution Provider Device Support * Introduced Python bindings for `OrtSyncStream`, including creation via `OrtEpDevice.create_sync_stream()` and retrieval of device-specific `OrtMemoryInfo` via `OrtEpDevice.memory_info()`. [[1]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR1890-R1938) [[2]](diffhunk://#diff-44e70fbe60cba71c94f1a46ec2b1facaa8e9475232dad6df5ecbea301e76d475R34-R44) * Refactored the C++ API to generalize `SyncStream` handling, allowing for unowned streams and improved type safety. [[1]](diffhunk://#diff-17f64e8b38fcdcd25e90abcabeec4b420956b15fe63868a5d0b270c376bde209L1066-R1084) [[2]](diffhunk://#diff-cc93f5f9d8078d3d3af14c9bb4c0c59e25a99f3ec75d7772ea20111ed7eb6ddeL672-R677) ### Tensor Copy Functionality * Added a new Python-level `copy_tensors` function and corresponding C++ binding, enabling efficient copying of tensor data between `OrtValue` objects, optionally using a synchronization stream. [[1]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR1588-R1599) [[2]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR1155-R1163) [[3]](diffhunk://#diff-44e70fbe60cba71c94f1a46ec2b1facaa8e9475232dad6df5ecbea301e76d475R84) ### Miscellaneous Improvements and Fixes * Changed the return type of the `OrtValue.data_ptr` method in the Python binding from `int64_t` to `uintptr_t` for better cross-platform compatibility. [[1]](diffhunk://#diff-666c9002698d1bbd4215237231e5be98d7b33e5054f018dce952407027bd0473L336-R336) [[2]](diffhunk://#diff-666c9002698d1bbd4215237231e5be98d7b33e5054f018dce952407027bd0473L347-R347) * Minor improvements to error messages and device type handling in the Python API (e.g., for `OrtDevice`). [[1]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR1176) [[2]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR1219-R1221) * Included necessary C++ includes for plugin stream support. These changes collectively improve the flexibility and introspection capabilities of ONNX Runtime's device, memory, and execution provider interfaces, and make advanced features available to Python users. ### Motivation and Context  Depends on: #26021

### Description  This fixes somewhat contrived edgecases that are present in our tests - input propagates to output - output is produced by an initializer. ### Motivation and Context  Python API upcoming PR does not pass tests without it.

### Description  This pull request introduces several enhancements to ONNX Runtime's Python and C++ APIs, focusing on improved device and memory information handling, synchronization stream support, and tensor copy functionality. It adds new Python bindings for device/memory types, exposes more detailed session input/output metadata, and provides a Python-accessible tensor copy API. The changes also refactor and extend the C++ API for better stream and memory info management. Key changes include: ### Device and Memory Information Enhancements * Added Python bindings for `OrtMemoryInfoDeviceType`, `OrtDeviceMemoryType`, and expanded `OrtDevice` to expose the memory type via a new `mem_type` method. The `OrtMemoryInfo` Python class now supports both legacy and new V2 constructors and exposes additional properties such as device memory type and vendor ID. [[1]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR1801-R1810) [[2]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR1839) [[3]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eL1941-R2005) * Extended the Python `InferenceSession` object to provide access to input/output `OrtMemoryInfo` and `OrtEpDevice` objects through new properties and methods. [[1]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR2702-R2729) [[2]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR202-R213) [[3]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR591-R593) [[4]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR607-R609) ### Synchronization Stream and Execution Provider Device Support * Introduced Python bindings for `OrtSyncStream`, including creation via `OrtEpDevice.create_sync_stream()` and retrieval of device-specific `OrtMemoryInfo` via `OrtEpDevice.memory_info()`. [[1]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR1890-R1938) [[2]](diffhunk://#diff-44e70fbe60cba71c94f1a46ec2b1facaa8e9475232dad6df5ecbea301e76d475R34-R44) * Refactored the C++ API to generalize `SyncStream` handling, allowing for unowned streams and improved type safety. [[1]](diffhunk://#diff-17f64e8b38fcdcd25e90abcabeec4b420956b15fe63868a5d0b270c376bde209L1066-R1084) [[2]](diffhunk://#diff-cc93f5f9d8078d3d3af14c9bb4c0c59e25a99f3ec75d7772ea20111ed7eb6ddeL672-R677) ### Tensor Copy Functionality * Added a new Python-level `copy_tensors` function and corresponding C++ binding, enabling efficient copying of tensor data between `OrtValue` objects, optionally using a synchronization stream. [[1]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR1588-R1599) [[2]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR1155-R1163) [[3]](diffhunk://#diff-44e70fbe60cba71c94f1a46ec2b1facaa8e9475232dad6df5ecbea301e76d475R84) ### Miscellaneous Improvements and Fixes * Changed the return type of the `OrtValue.data_ptr` method in the Python binding from `int64_t` to `uintptr_t` for better cross-platform compatibility. [[1]](diffhunk://#diff-666c9002698d1bbd4215237231e5be98d7b33e5054f018dce952407027bd0473L336-R336) [[2]](diffhunk://#diff-666c9002698d1bbd4215237231e5be98d7b33e5054f018dce952407027bd0473L347-R347) * Minor improvements to error messages and device type handling in the Python API (e.g., for `OrtDevice`). [[1]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR1176) [[2]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR1219-R1221) * Included necessary C++ includes for plugin stream support. These changes collectively improve the flexibility and introspection capabilities of ONNX Runtime's device, memory, and execution provider interfaces, and make advanced features available to Python users. ### Motivation and Context  Depends on: #26021

### Description  This fixes somewhat contrived edgecases that are present in our tests - input propagates to output - output is produced by an initializer. ### Motivation and Context  Python API upcoming PR does not pass tests without it.

### Description  This pull request introduces several enhancements to ONNX Runtime's Python and C++ APIs, focusing on improved device and memory information handling, synchronization stream support, and tensor copy functionality. It adds new Python bindings for device/memory types, exposes more detailed session input/output metadata, and provides a Python-accessible tensor copy API. The changes also refactor and extend the C++ API for better stream and memory info management. Key changes include: ### Device and Memory Information Enhancements * Added Python bindings for `OrtMemoryInfoDeviceType`, `OrtDeviceMemoryType`, and expanded `OrtDevice` to expose the memory type via a new `mem_type` method. The `OrtMemoryInfo` Python class now supports both legacy and new V2 constructors and exposes additional properties such as device memory type and vendor ID. [[1]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR1801-R1810) [[2]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR1839) [[3]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eL1941-R2005) * Extended the Python `InferenceSession` object to provide access to input/output `OrtMemoryInfo` and `OrtEpDevice` objects through new properties and methods. [[1]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR2702-R2729) [[2]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR202-R213) [[3]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR591-R593) [[4]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR607-R609) ### Synchronization Stream and Execution Provider Device Support * Introduced Python bindings for `OrtSyncStream`, including creation via `OrtEpDevice.create_sync_stream()` and retrieval of device-specific `OrtMemoryInfo` via `OrtEpDevice.memory_info()`. [[1]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR1890-R1938) [[2]](diffhunk://#diff-44e70fbe60cba71c94f1a46ec2b1facaa8e9475232dad6df5ecbea301e76d475R34-R44) * Refactored the C++ API to generalize `SyncStream` handling, allowing for unowned streams and improved type safety. [[1]](diffhunk://#diff-17f64e8b38fcdcd25e90abcabeec4b420956b15fe63868a5d0b270c376bde209L1066-R1084) [[2]](diffhunk://#diff-cc93f5f9d8078d3d3af14c9bb4c0c59e25a99f3ec75d7772ea20111ed7eb6ddeL672-R677) ### Tensor Copy Functionality * Added a new Python-level `copy_tensors` function and corresponding C++ binding, enabling efficient copying of tensor data between `OrtValue` objects, optionally using a synchronization stream. [[1]](diffhunk://#diff-c46fc0e05521f706449c04aed599ac0229012c007a78b584519e71a57601d63eR1588-R1599) [[2]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR1155-R1163) [[3]](diffhunk://#diff-44e70fbe60cba71c94f1a46ec2b1facaa8e9475232dad6df5ecbea301e76d475R84) ### Miscellaneous Improvements and Fixes * Changed the return type of the `OrtValue.data_ptr` method in the Python binding from `int64_t` to `uintptr_t` for better cross-platform compatibility. [[1]](diffhunk://#diff-666c9002698d1bbd4215237231e5be98d7b33e5054f018dce952407027bd0473L336-R336) [[2]](diffhunk://#diff-666c9002698d1bbd4215237231e5be98d7b33e5054f018dce952407027bd0473L347-R347) * Minor improvements to error messages and device type handling in the Python API (e.g., for `OrtDevice`). [[1]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR1176) [[2]](diffhunk://#diff-f0e8ba8cb8cb07b51b3be675bf62cec07e2eae1461341ce5801d33a57c8f57fdR1219-R1221) * Included necessary C++ includes for plugin stream support. These changes collectively improve the flexibility and introspection capabilities of ONNX Runtime's device, memory, and execution provider interfaces, and make advanced features available to Python users. ### Motivation and Context  Depends on: #26021

### Description Cherry-pick the following PRs into the ORT 1.23.1 branch: - Fix Attention GQA implementation on CPU - **MANUAL MERGE**: see #26057 - main merge date: Sept 15, 11:33am - pr: #25966 - commit: d530b29 - Address edge GetMemInfo edge cases - main merge date: Sept 16, 10:32am - pr: #26021 - commit: d251f3a - Implement new Python APIs - main merge date: Sept 17, 11:44am - pr: #25999 - commit: abc63e8 - MemcpyFromHost and MemcpyToHost support for plugin EPs - **MERGE CONFLICT** on file onnxruntime/test/optimizer/transpose_optimizer_test.cc. Conflicts with #25689 - main merge date: Sept 23, 10:42am - pr: #26088 - commit: 4545732 - [TRT RTX EP] Fix bug for generating the correct subgraph in GetCapability #26132 - main merge date: Sept 23, 8:54pm - pr: #26132 - commit: 72e56e7 ### Motivation and Context  --------- Co-authored-by: Dmitri Smirnov <yuslepukhin@users.noreply.github.com> Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com> Co-authored-by: Chi Lo <54722500+chilo-ms@users.noreply.github.com>

### Description - Regenerates the `input_propagate_to_output.onnx` model used in [this unit test](https://github.com/microsoft/onnxruntime/blob/35dcab5088118117acc6086c9b6dd6dd92c7060f/onnxruntime/test/shared_lib/test_inference.cc#L497-L506) so that it uses an ONNX IR version compatible with ONNX 1.18.0 (i.e., IR version < 12). - Adds script `input_propagate_to_output.py` that can be used to regenerate the `input_propagate_to_output.onnx` model. - Embed missing weight values that are needed to run the existing `test_dangling_input_segment_ids.py` script. ### Motivation and Context The main branch is using ONNX 1.19. However, this unit test also needs to pass in the `rel-1.23.1` branch, which is still using ONNX 1.18.0. So, by downgrading the model's IR version, the unit test can run in both branches. See original PR that added the test models: #26021

snnn · 2025-09-25T22:45:12Z

This PR has been cherry-picked into the rel-1.23.1 branch in PR #26140. Removing the release:1.23.1 label.

### Description - Regenerates the `input_propagate_to_output.onnx` model used in [this unit test](https://github.com/microsoft/onnxruntime/blob/35dcab5088118117acc6086c9b6dd6dd92c7060f/onnxruntime/test/shared_lib/test_inference.cc#L497-L506) so that it uses an ONNX IR version compatible with ONNX 1.18.0 (i.e., IR version < 12). - Adds script `input_propagate_to_output.py` that can be used to regenerate the `input_propagate_to_output.onnx` model. - Embed missing weight values that are needed to run the existing `test_dangling_input_segment_ids.py` script. ### Motivation and Context The main branch is using ONNX 1.19. However, this unit test also needs to pass in the `rel-1.23.1` branch, which is still using ONNX 1.18.0. So, by downgrading the model's IR version, the unit test can run in both branches. See original PR that added the test models: #26021

* ORT 1.23.1 cherrypick 1 [REDO] (microsoft#26140) ### Description Cherry-pick the following PRs into the ORT 1.23.1 branch: - Fix Attention GQA implementation on CPU - **MANUAL MERGE**: see microsoft#26057 - main merge date: Sept 15, 11:33am - pr: microsoft#25966 - commit: d530b29 - Address edge GetMemInfo edge cases - main merge date: Sept 16, 10:32am - pr: microsoft#26021 - commit: d251f3a - Implement new Python APIs - main merge date: Sept 17, 11:44am - pr: microsoft#25999 - commit: abc63e8 - MemcpyFromHost and MemcpyToHost support for plugin EPs - **MERGE CONFLICT** on file onnxruntime/test/optimizer/transpose_optimizer_test.cc. Conflicts with microsoft#25689 - main merge date: Sept 23, 10:42am - pr: microsoft#26088 - commit: 4545732 - [TRT RTX EP] Fix bug for generating the correct subgraph in GetCapability microsoft#26132 - main merge date: Sept 23, 8:54pm - pr: microsoft#26132 - commit: 72e56e7 ### Motivation and Context  --------- Co-authored-by: Dmitri Smirnov <yuslepukhin@users.noreply.github.com> Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com> Co-authored-by: Chi Lo <54722500+chilo-ms@users.noreply.github.com> * ORT 1.23.1 cherrypick 2 (microsoft#26182) ### Description Adds the following commits to the `rel-1.23.1` branch for ORT 1.23.1: - add session_id_ to LogEvaluationStart/Stop, LogSessionCreationStart - main merge date: July 31, 1:05am - pr: microsoft#25590 - commit: e753643 - [build] fix WebAssembly build on macOS/arm64 - main merge date: Aug 5, 8:07am - pr: microsoft#25653 - commit: 53f152b - [CPU] MoE Kernel (microsoft#25958) - main merge date: Sept 10, 4:54pm - pr: microsoft#25958 - commit: 930e640 - [CPU] Block-wise QMoE kernel for CPU - main merge date: Sept 15, 8:32am - pr: microsoft#26009 - commit: 5d17734 - [C#] Implement missing APIs - main merge date: Sept 24, 10:50am - pr: microsoft#26101 - commit: 35dcab5 - Regenerate test model with ONNX IR < 12 - main merge date: Sept 24, 2:50pm - pr: microsoft#26149 - commit: 88f2652 - [CPU] Fix compilation errors because of unused variables - main merge date: Sept 25, 1:21pm - pr: microsoft#26147 - commit: 42fcd71 - [EP ABI] Check if nodes specified in GetCapability() have already been assigned - main merge date: Sept 26, 1:24am - pr: microsoft#26156 - commit: 67d3ba0 - [QNN EP] Add dynamic option to set HTP performance mode - main merge date: Sept 26, 11:55am - pr: microsoft#26135 - commit: 6cc40fd --------- Co-authored-by: xieofxie <xieofxie@126.com> Co-authored-by: hualxie <hualxie@microsoft.com> Co-authored-by: Yulong Wang <7679871+fs-eire@users.noreply.github.com> Co-authored-by: Akshay Sonawane <111780983+apsonawane@users.noreply.github.com> Co-authored-by: Dmitri Smirnov <yuslepukhin@users.noreply.github.com> Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com> Co-authored-by: quic-tirupath <quic_tirupath@quicinc.com> Co-authored-by: quic-ashwshan <quic_ashwshan@quicinc.com> --------- Co-authored-by: Adrian Lizarraga <adlizarraga@microsoft.com> Co-authored-by: Dmitri Smirnov <yuslepukhin@users.noreply.github.com> Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com> Co-authored-by: Chi Lo <54722500+chilo-ms@users.noreply.github.com> Co-authored-by: xieofxie <xieofxie@126.com> Co-authored-by: hualxie <hualxie@microsoft.com> Co-authored-by: Yulong Wang <7679871+fs-eire@users.noreply.github.com> Co-authored-by: Akshay Sonawane <111780983+apsonawane@users.noreply.github.com> Co-authored-by: quic-tirupath <quic_tirupath@quicinc.com> Co-authored-by: quic-ashwshan <quic_ashwshan@quicinc.com>

Address edge cases when

a27910c

- input propagates to output - output is produced by an initialier.

yuslepukhin requested review from Copilot and skottmckay September 12, 2025 02:45

Copilot AI reviewed Sep 12, 2025

View reviewed changes

onnxruntime/core/session/inference_session.cc Show resolved Hide resolved

onnxruntime/core/session/inference_session.cc Show resolved Hide resolved

yuslepukhin requested a review from edgchen1 September 12, 2025 17:12

yuslepukhin added 3 commits September 15, 2025 10:45

Account for unlikely dnagling inputs (unconsumed)

c30f06b

Merge branch 'main' into yuslepukhin/fix_getmeminfo_edge_cases

a36db2d

Fix test model path

9f4381e

skottmckay reviewed Sep 15, 2025

View reviewed changes

onnxruntime/core/session/inference_session.cc Show resolved Hide resolved

edgchen1 reviewed Sep 15, 2025

View reviewed changes

include/onnxruntime/core/session/onnxruntime_cxx_inline.h Show resolved Hide resolved

onnxruntime/core/session/inference_session.cc Show resolved Hide resolved

onnxruntime/test/testdata/input_propagated_to_output.onnx Show resolved Hide resolved

Address review comments

455b786

github-advanced-security bot found potential problems Sep 15, 2025

View reviewed changes

onnxruntime/test/testdata/test_dangling_input_segment_ids.py Fixed Show fixed Hide fixed

onnxruntime/test/testdata/test_dangling_input_segment_ids.py Fixed Show fixed Hide fixed

onnxruntime/test/testdata/test_dangling_input_segment_ids.py Fixed Show fixed Hide fixed

github-advanced-security bot found potential problems Sep 15, 2025

View reviewed changes

onnxruntime/test/testdata/test_dangling_input_segment_ids.py Fixed Show fixed Hide fixed

skottmckay previously approved these changes Sep 16, 2025

View reviewed changes

Lint

2891999

yuslepukhin dismissed skottmckay’s stale review via 2891999 September 16, 2025 01:19

github-advanced-security bot found potential problems Sep 16, 2025

View reviewed changes

edgchen1 approved these changes Sep 16, 2025

View reviewed changes

yuslepukhin merged commit d251f3a into main Sep 16, 2025
87 of 91 checks passed

yuslepukhin deleted the yuslepukhin/fix_getmeminfo_edge_cases branch September 16, 2025 17:32

yuslepukhin mentioned this pull request Sep 16, 2025

Implement new Python APIs #25999

Merged

yuslepukhin added the release:1.23.1 label Sep 22, 2025

adrianlizarraga mentioned this pull request Sep 24, 2025

ORT 1.23.1 cherrypick 1 #26138

Closed

adrianlizarraga mentioned this pull request Sep 24, 2025

ORT 1.23.1 cherrypick 1 [REDO] #26140

Merged

adrianlizarraga mentioned this pull request Sep 24, 2025

Regenerate test model with ONNX IR < 12 #26149

Merged

snnn removed the release:1.23.1 label Sep 25, 2025

@@ -9,7 +9,6 @@
             import numpy as np
             import onnx
-            from onnx import TensorProto, helper, numpy_helper
             DATA_DIR = os.path.join(os.path.dirname(os.path.realpath(__file__)), "test_dangling_input_segment_ids")
@@ -20,7 +19,7 @@
             def make_node(op_type, inputs, outputs, name=None, doc_string=None, domain=None, **kwargs):
-                node = helper.make_node(op_type, inputs, outputs, name, doc_string, domain, **kwargs)
+                node = onnx.helper.make_node(op_type, inputs, outputs, name, doc_string, domain, **kwargs)
                 if doc_string == "":
                     node.doc_string = ""
                 order_repeated_field(node.attribute, "name", kwargs.keys())
@@ -28,42 +27,42 @@
             def make_graph(*args, doc_string=None, **kwargs):
-                graph = helper.make_graph(*args, doc_string=doc_string, **kwargs)
+                graph = onnx.helper.make_graph(*args, doc_string=doc_string, **kwargs)
                 if doc_string == "":
                     graph.doc_string = ""
                 return graph
-            model = helper.make_model(
-                opset_imports=[helper.make_operatorsetid("", 14), helper.make_operatorsetid("com.microsoft", 1)],
+            model = onnx.helper.make_model(
+                opset_imports=[onnx.helper.make_operatorsetid("", 14), onnx.helper.make_operatorsetid("com.microsoft", 1)],
                 ir_version=7,
                 graph=make_graph(
                     name="embed_layernorm_graph",
                     inputs=[
-                        helper.make_tensor_value_info("input_ids", TensorProto.INT32, shape=[1, 4]),
-                        helper.make_tensor_value_info("segment_ids", TensorProto.INT32, shape=[1, 4]),
+                        onnx.helper.make_tensor_value_info("input_ids", onnx.TensorProto.INT32, shape=[1, 4]),
+                        onnx.helper.make_tensor_value_info("segment_ids", onnx.TensorProto.INT32, shape=[1, 4]),
                     ],
                     outputs=[
-                        helper.make_tensor_value_info("layernorm_out", TensorProto.FLOAT, shape=[1, 4, 4]),
-                        helper.make_tensor_value_info("mask_index_out", TensorProto.INT32, shape=[1]),
+                        onnx.helper.make_tensor_value_info("layernorm_out", onnx.TensorProto.FLOAT, shape=[1, 4, 4]),
+                        onnx.helper.make_tensor_value_info("mask_index_out", onnx.TensorProto.INT32, shape=[1]),
                     ],
                     initializer=[
-                        numpy_helper.from_array(
+                        onnx.numpy_helper.from_array(
                             np.load(os.path.join(DATA_DIR, "const0_word_embed.npy")).astype("float32").reshape([32, 4]),
                             name="word_embed",
                         ),
-                        numpy_helper.from_array(
+                        onnx.numpy_helper.from_array(
                             np.load(os.path.join(DATA_DIR, "const1_pos_embed.npy")).astype("float32").reshape([16, 4]),
                             name="pos_embed",
                         ),
-                        numpy_helper.from_array(
+                        onnx.numpy_helper.from_array(
                             np.array(
                                 [0.6185135841369629, 0.010364261455833912, 0.5386272668838501, 0.0030179566238075495],
                                 dtype="float32",
                             ),
                             name="gamma",
                         ),
-                        numpy_helper.from_array(
+                        onnx.numpy_helper.from_array(
                             np.array(
                                 [0.9511938095092773, 0.9054020047187805, 0.7959669232368469, 0.9152743220329285], dtype="float32"
                             ),

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Address edge GetMemInfo edge cases #26021

Address edge GetMemInfo edge cases #26021

Uh oh!

yuslepukhin commented Sep 12, 2025

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

skottmckay left a comment

Uh oh!

Check notice

Copilot Autofix

Uh oh!

snnn commented Sep 25, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Address edge GetMemInfo edge cases #26021

Address edge GetMemInfo edge cases #26021

Uh oh!

Conversation

yuslepukhin commented Sep 12, 2025

Description

Motivation and Context

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull Request Overview

Reviewed Changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

skottmckay left a comment

Choose a reason for hiding this comment

Uh oh!

Check notice

Copilot Autofix

Uh oh!

snnn commented Sep 25, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants