Skip to content

Releases: onnx/onnx

v1.20.0

01 Dec 17:14
@titaiwangms titaiwangms
v1.20.0
bca0315
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.20.0 Latest
Latest

ONNX v1.20.0 is now available with exciting new features! We would like to thank everyone who contributed to this release!
Please visit onnx.ai to learn more about ONNX and associated projects.

Updated Op list:

Cast, CastLike, Constant, ConstantOfShape, DequantizeLinear, Flatten, Identity, If, Loop, Pad, QuantizeLinear, Reshape, Scan, Shape, Size, Squeeze, Transpose, Unsqueeze

Key Updates:

  • Support for Python 3.14 via Python's stable ABI. (#7276)
  • Opset 25
  • 2-bit dtype support (#7446)
  • A new "node determinism" attribute in operator schemas (#7176)

Breaking Changes and Deprecations

  • Update manylinux_2014 -> manylinux_2_28 (#7151)
  • Update attention gqa to use repeat interleave within repeat kv (#7274)
  • Update required Python version to 3.10 and related fixes (#7220)
  • Remove Python 3.9 wheel build (#7217)
  • Remove deprecated methods (#7214)

Spec and Operator

  • Add 2 bit support to onnx (#7446)
  • Remove enforcement to node determinism attribute (#7473)
  • Fix handling of empty inputs for the Softmax operator (#7206)
  • Fix OneHotEncoder segfault due to missing input shape validation (#7302)
  • Fix Attention backend test: correct dimension of Range input (#7300)
  • Fix Range input rank in Attention op function definition (#7240)
  • Update Reduce op doc for empty axes (#7421)
  • Add additional test cases for MatMul operator (#7407)
  • Fix ScatterND spec (#7406)
  • Add node determinism attribute to operator schemas (#7176)

Reference Implementation

  • Fix division for integer dtype in reference implementation (#7203)
  • Fix noop_with_empty_axes in Reduce ops (#7394)
  • Fix warnings in testing (#7367)
  • Throw TypeError for invalid input types (#7366)
  • Rename variables in RotaryEmbedding reference for clarity (#7316)
  • Reference evaluator: treat empty axes as empty (#7244)
  • Clean up reference evaluator tests (#7238)

Utilities and Tools

  • Fix IsOnnxStaticRegistrationDisabled() inline function breaking schema registration in external modules (#7409)
  • Allow conversion from OpSchema to OpSchemaRegisterOnce (#7390)
  • Disable nanobind leak warnings in cpp2py_export (#7334)
  • Add additional 19 → 18 conversion supports (#7422)
  • Create 19 → 18 type op conversion (#7319)
  • Clean up shape inference imports (#7278)

Build, CI and Tests

  • Create CPPLINT.cfg (#7198)
  • Lift minimum Protobuf version for Python 3.14+ on macOS (#7419)
  • Downgrade reuse.yml (#7395)
  • Add CMake test (#7387)
  • Fix a syntactic error in ONNXConfig.cmake.in (#7385)
  • Enable Python 3.14 in main (#7384)
  • Update manylinux image in release_linux.yml (#7383)
  • Support Ninja builds (#7332)
  • Update pixi.lock file (#7331)
  • Fix CMake expression for find_package (#7295)
  • General CMake fixes (#7291)
  • Remove ml_dtypes from requirements-dev.txt (#7290)
  • Fix conditional for downloading artifacts in mac workflow (#7413)
  • Update release_mac.yml: change 3.14-dev to 3.14 (#7396)
  • Update release_mac.yml: skip pytest for 3.14-dev (#7369)
  • Add GitHub Actions security analysis with Zizmor (#7363)
  • Enable macOS + Python 3.13 test (#7330)
  • Fix testsuite failures on s390x (#7309)
  • Improve abi3audit checks in release_*.yml (#7293)
  • Add abi3audit to release_linux.yml (#7288)
  • Update pixi.{toml,lock} and create issues if CI fails (#7280)
  • Replace pybind11 with nanobind for Python stable ABI support (#7276)

Documentation

  • Add trademark information (README.md) (#7189)
  • Update RELEASE-MANAGEMENT.md (#7188)
  • Improve conditions in create_release.yml (#7186)
  • Improve release documentation (OnnxReleases.md) (#7187)
  • Improve OnnxReleases.md (#7202)
  • Add install command to OnnxReleases.md (#7204)
  • Add markdown file and diagram for in-place KV cache (#7205)
  • Bump versions for 1.20.0 (#7436)
  • Update IR VERSION 12 published date to August 26, 2025 (#7431)
  • Clean up pull request template comments (#7415)
  • Simplify upload instructions (#7414)
  • Add ONNX versions 1.16.1, 1.16.2, and 1.19.1 (#7411)
  • Update versioning information in Versioning.md (#7410)
  • Improve documentation formatting (#7408)
  • Update transpose documentation (#7405)
  • Add copyright and license information to main.cc (#7397)
  • Update LAST_RELEASE_VERSION to 1.19.1 (missed in last version) (#7391)
  • Explicitly specify the Google Python Style Guide in CONTRIBUTING.md (#7381)
  • Update RELEASE-MANAGEMENT.md (#7380)
  • Update .editorconfig check to include YAML and Markdown files (#7370)
  • Improve markdown files (#7368)
  • Update data_location docs to match onnx.in.proto (#7347)
  • Add abi3 information to README.md (#7289)
  • Update OnnxReleases.md with correct pipeline configs (#7252)
  • Update figures and RELEASE-MANAGEMENT.md (#7250)
  • Update RELEASE-MANAGEMENT.md (#7239)
  • Add reproducible builds section to README.md (#7237)
  • Fix release condition in create_release.yml (#7230)
  • Update RELEASE-MANAGEMENT.md (#7216)
Assets 2
Loading

v1.19.1

10 Oct 02:06
@yuanyao-nv yuanyao-nv
v1.19.1
b751946
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.19.1

Note

This patch release includes important bug fixes to the function definition of Attention-23/24 under the Group Query Attention mode and to the reference implementation of RotaryEmbedding-23.

All changes

  • Avoid unnecessary re-generating of proto files (#7253) in #7306
  • Require ml_dtypes>=0.5.0 (#7254) in #7307
  • Cherry pick four attention PRs in #7315
  • Update rotary_embedding reference implementation and tests (#7304, #7316) in #7313
  • Override __repr__ for some proto classes (#7259) in #7314
  • add check for rc-candidates (Update create_release.yml) (#7261) in #7323
  • Implement repr methods for Model/Graph/Function (#7320) in #7325
Loading

v1.19.0

26 Aug 21:48
@yuanyao-nv yuanyao-nv
v1.19.0
57b9c6a
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.19.0

ONNX v1.19.0 is now available with exciting new features! We would like to thank everyone who contributed to this release!
Please visit onnx.ai to learn more about ONNX and associated projects.

Key Updates

IR Version 12

  • Added FLOAT8E8M0 type

ai.onnx Opset 24

  • Added Swish op
  • Added TensorScatter op and updated Attention op for in-place KV cache updates
  • Enabled FLOAT8E8M0 for QuantizeLinear, DequantizeLinear, Cast, CastLike, Constant, ConstantOfShape, Identity, Reshape, Shape, Size, If, Loop, Scan, Flatten, Pad, Squeeze, Unsqueeze, and Transpose.
  • Enabled BF16 for TopK and SplitToSequence.

Other

  • Added dependency on ml-dtypes
  • BUILD_ONNX_PYTHON symbol is deprecated (we be removed for 1.20). Please, use ONNX_BUILD_PYTHON instead.

What's Changed

Breaking Changes and Deprecations

Spec and Operator

  • Clarify the axes input of [un]Squeeze to be 1D tensors by @justinchuby in #6888
  • Clarify that variable shadowing is not allowed by @justinchuby in #6955
  • Clarify Mod operator by @cbourjau in #6973
  • Fix typo regarding Attention scale in the spec by @yuanyao-nv in #6984
  • Clarify default value for ratio input of Dropout operator by @robertknight in #7032
  • Correct dtype attribute docs for EyeLike operator by @robertknight in #7031
  • Update float8 table for the Cast op spec by @justinchuby in #7085
  • Document Multi-Device Configuration proto specifications in IR.md by @Copilot in #7056
  • Add FLOAT8E8M0 data type by @yuanyao-nv in #7030
  • Enable float8e8m0 for Q/DQ, and other ops by @yuanyao-nv in #7120
  • Update the saturating behavior for E4M3FNUZ/E5M2FNUZ in Cast and CastLike by @justinchuby in #7130
  • Fix ELU and Softplus operators to support tensors of any shape by @Copilot in #7136
  • Fix Shape operator specification: correct range bounds and document start > end behavior by @Copilot in #7132
  • Fix Attention 3D, reference implementation and c++ expansion by @xadupre in #7142
  • Fix RMS norm function definition by @justinchuby in #7135
  • Fix spec for ReduceSumSquare and other reduce ops when noop_with_empty_axes is set by @Copilot in #7137
  • Add bf16 support to TopK and SplitToSequence by @gramalingam in #7158
  • Add Swish operator by @isdanni in #7172
  • Add TensorScatter op for in-place kv cache update by @yuanyao-nv in #7114
  • Fix Resize operator document by @kcvlex in #6686
  • Add kv_nonpad_seqlen input to Attention by @yuanyao-nv in #7164

Reference Implementation

Utilities and Tools

  • Support set schema inference function in python by @OYCN in #5940
  • Improve model Extractor by @justinchuby in #6920
  • Fix: prefixing of graphs when rename_inputs=False/rename_outputs=False by @KarelZe in #6994
  • Fix Einsum shape inference segfault for scalar inputs by @Copilot in #7055
  • Add support for constructing functions with graph attributes by @Copilot in #7112
  • Make some op-level shape inference functions public by @titaiwangms in #7091
  • Implement saturate_cast in numpy helper by @justinchuby in #7143
  • Add .txtpb as a support text proto format in serialization by @justinchuby in #7161

Build, CI and Tests

Documentation

Other Changes

Read more

Contributors

robertknight, ktf, and 29 other contributors
Loading

v1.18.0

12 May 23:07
@ramkrishna2910 ramkrishna2910
v1.18.0
e709452
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.18.0

ONNX v1.18.0 is now available with exciting new features! We would like to thank everyone who contributed to this release!
Please visit onnx.ai to learn more about ONNX and associated projects.

Key Updates

ai.onnx Opset 23

Attention, Cast, CastLike, Constant, ConstantOfShape, DequantizeLinear, Flatten, Identity, If, Loop, Pad, QuantizeLinear, RMSNormalization, Reshape, RotaryEmbedding, Scan, Shape, Size, Squeeze, Transpose, Unsqueeze

IR Version 11

  • Added FLOAT4E2M1 and multi-device configuration support
  • Relaxed naming requirements (#6652)

Python support

  • Support Python 3.13
  • Experimental support for Python 3.13t (Windows, Mac)
  • Removed support for Python 3.8
  • wheels for Windows Arm64

Build

  • Minimum protobuf version is upgraded to v25.1
  • A new option ONNX_BUILD_CUSTOM_PROTOBUF is added for CMAKE (#6495)

What's Changed

Breaking Changes and Deprecations

  • Remove/raise exception when external file exists during onnx.save by @tonypottera24 in #6497
  • Remove python 3.8 workflows (python 3.8 is eol) by @cyyever in #6434
  • Deprecate all type casting functions by @justinchuby in #6639 => scheduled to remove in 1.20
  • GroupNormalization-18 is now deprecated and replaced by GroupNormalization-23 due to an incorrect definition (#6358)
  • helper.split_complex_to_pairs is now private. Users can consider duplicating the underlying logic for their own use.

Spec and Operator

Reference Implementation

Utilities and Tools

Build, CI and Tests

Documentation

  • Move INSTALL instruction to separate file by @andife in #6560
  • Fix Pad operator example in Python API docs (correct attribute usage) by @kolasaniv1996 in #6702

Other Changes

  • Remove unused variables by @cyyever in #6303
  • Fix main url checks by @roborags in #6312
  • Bumped main VERSION_NUMBER to 1.18.0 by @roborags in #6315
  • Bump ai.onnx opset to 23 by @roborags in #6316
  • Combine different release pipelines by the use of reusable workflows by @andife in #6277
  • Bump actions/upload-artifact from 3 to 4 by @andife in #6319
  • Fix missing secrets for publishing of onnxweekly by @andife in #6321
  • Update main.yml (upgrade github actions download/upload artifact) by @andife in #6320
  • BF: fix condition for publishing to testpypi (Update create_release.yml) by @andife in #6338
  • Fix OOB in data propagation of math ops when input is broadcasted to zero by @Yosshi999 in #6323
  • The latest protobuf pkg 5.28.0 is failing on Windows. use the one pre… by @liqunfu in #6342
  • Set up codecov test analysis by @justinchuby in #6345
  • Fix model extraction utility by @gramalingam in #6344
  • Add missing matrix.target-architecture ? (Update release_mac.yml) by @andife in #6350
  • Some performance fixes in C++ code, use of emplace instead of insert by @cyyever in #6304
  • Fix some clang-tidy warnings by @cyyever in #6353
  • BugFix: make sure that unique files names are used before uploading the wheels b...
Read more

Contributors

mgorny, petewarden, and 31 other contributors
Loading

v1.17.0

01 Oct 17:57
@roborags roborags
v1.17.0
b8baa84
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.17.0

ONNX v1.17.0 is now available with exciting new features! We would like to thank everyone who contributed to this release!
Please visit onnx.ai to learn more about ONNX and associated projects.

Key Updates

ai.onnx Opset 22

Python Changes

  • Support for numpy >= 2.0

Bug fixes and infrastructure improvements

  • Fix Check URLs errors 5972
  • Use CMAKE_PREFIX_PATH in finding libprotobuf 5975
  • Bump main VERSION_NUMBER to 1.17.0 5968
  • Fix source and pip tar.gz builds on s390x systems 5984
  • Fix unique_name 5992
  • Fix SegFault bug in shape inference 5990
  • Fix onnx.compose when connecting subgraphs 5991
  • Fix conversion from split 11 to split 18 6020
  • Update error messages for NegativeLogLikelihoodLoss inference function 6021
  • Generalize input/output number check in shape inference 6005
  • Replace rank inference with shape inference for Einsum op 6010
  • build from source instruction with latest cmake change 6038
  • Handle OneHot's depth value during shape inference 5963
  • Not to install cmake in pyproject.toml on Windows 6045
  • fix a skipped shape infer code 6049
  • Include the ".onnxtext" extension in supported serialization format 6051
  • Allow ReferenceEvaluator to return intermediate results 6066
  • Fix 1 typo in numpy_helper.py 6041
  • Remove benchmarking code 6076
  • Prevent crash on import after GCC 8 builds 6048
  • Check graph outputs are defined 6083
  • Enable additional ruff rules 6032
  • Add missing shape inference check for DequantizeLinear 6080
  • Add bfloat16 to all relevant ops 6099
  • fix(ci): install python dependencies with --only-binary :all: in manylinux 6120
  • fix: install google-re2 with --only-binary option 6129
  • Specify axis parameter for DequantizeLinear when input rank is 1 6095
  • Pin onnxruntime to 1.17.3 for release CIs 6143
  • Fix INT4 TensorProto byte size is 5x larger than expected with negative values 6161
  • Mitigate tarball directory traversal risks 6164
  • Fix reference implementation for ScatterND with 4D tensors 6174
  • Addition of group > 1 in test and in backend for ConvTranspose 6175
  • Support for bfloat16 for binary, unary operators in reference implementation 6166
  • Refactor windows workflow to work on standard windows 6190
  • Fix a few crashes while running shape inference 6195
  • Update onnx to work with numpy>=2.0 6196
  • Use sets to improve performance of dfs search 6213
  • Upgrade reuse to v4.0.0 6216
  • Makes to_array, from_array support custom numpy dtype, support float16 type in parser 6170
  • Handle functions in external data helper 6233
  • Refactor safe extract method to fix issue 6215 6222
  • move examples dir 6230
  • Use MACOSX_DEPLOYMENT_TARGET=12.0 for macOS wheels 6242
  • Handle the optional input in infer_node_outputs 6250
  • Add check on dimensions in Gemm opset 6 6217
  • Update broken URLs 6255
  • The latest protobuf pkg 5.28.0 is failing on Windows. use the one pre… 6342
  • Remove unused variables 6303

Test improvements

  • Migrate CI to use Github Actions 6075
  • Add shape inference test for custom op 6068
  • chore(ci): build and test macOS universal2 wheels on macOS arm64 6117
  • Fix input names for quantize/dequantize ONNX backend tests 6122
  • Verify model deletion after testing 6127
  • Better name for Github Action and fix Windows build on CI 6173
  • Fix CI on Windows 3.12 6179
  • Rename test name with duplicated names, add logic to check it does not happen again 6194

Documentation updates

  • Fix typos in the comments and documentation 5944
  • Add more partner projects to be notified about new releases 6042
  • Update release process documentation 6043
  • Update CI pipeline README 6086
  • Add/Format License/Copyright headers [612...
Read more
Loading

v1.16.2

01 Aug 13:15
@cjvolzka cjvolzka
v1.16.2
3bf92c0
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.16.2

ONNX v1.16.2 is a patch release based on v1.16.1.

Bug fixes

  • Mitigate tarball directory traversal risks #6164
  • Refactor safe extract method #6222
  • Add check on dimensions in Gemm opset 6 #6217
  • Update broken URLs #6255

Please visit onnx.ai to learn more about ONNX and associated projects.

Loading

v1.16.1

23 May 17:50
@cjvolzka cjvolzka
v1.16.1
595228d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.16.1

ONNX v1.16.1 is a patch release based on v1.16.0.

Bug fixes

  • Prevent crash on import after GCC 8 builds #6048
  • Add missing shape inference check for DequantizeLinear #6080
  • Fix input names for quantize/dequantize ONNX backend tests #6122
  • fix a skipped shape infer code #6049

Please visit onnx.ai to learn more about ONNX and associated projects.

Loading

v1.16.0

25 Mar 15:40
@cjvolzka cjvolzka
v1.16.0
990217f
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.16.0

ONNX v1.16.0 is now available with exciting new features! We would like to thank everyone who contributed to this release! Please visit onnx.ai to learn more about ONNX and associated projects.

Key Updates

ai.onnx Opset 21

ai.onnx.ml Opset 4

IR Version 10

  • Added support for UINT4, INT4 types
  • GraphProto, FunctionProto, NodeProto, TensorProto added metadata_props field
  • FunctionProto added value_info field
  • FunctionProto and NodeProto added overload field to support overloaded functions.

Python Changes

  • Support registering custom OpSchemas via Python interface
  • Support Python3.12

Security Updates

  • Fix path sanitization bypass leading to arbitrary read (CVE-2024-27318)
  • Fix Out of bounds read due to lack of string termination in assert (CVE-2024-27319)

Deprecation notice

Bug fixes and infrastructure improvements

  • Enable empty list of values as attribute (#5559)
  • Add backward conversions from 18->17 for reduce ops (#5606)
  • DFT-20 version converter (#5613)
  • Fix version-converter to generate valid identifiers (#5628)
  • Reserve removed proto fields (#5643)
  • Cleanup shape inference implementation (#5596)
  • Do not use LFS64 on non-glibc linux (#5669)
  • Drop "one of" default attribute check in LabelEncoder (#5673)
  • TreeEnsemble base values for the reference implementation (#5665)
  • Parser/printer support external data format (#5688)
  • [cmake] Place export target file in the correct directory (#5677)
  • Bump CMAKE_CXX_STANDARD as 17 globally (#5612)
  • Fix shape inference for DequantizeLinear (#5709)
  • Fix swapped version numbers in version converter (#5734)
  • Expose LexicalScopeContext in checker.py (#5693)
  • Create in-memory large models without serializing large initializers through protobuf (#5685)
  • Define all in onnx.reference (#5749)
  • Add default for check_function & Use lexical_scope_ctx for readability (#5757)
  • Make ReferenceEvaluator support ModelContainer (#5754)
  • Fix reference implementation for loops with optional number of iterations (#5752)
  • Print the actual and expected attribute types in checker (#5762)
  • Resurrect check function context logic (#5778)
  • Fix conversion to zero for E4M3FNUZ and E5M2FNUZ (#5764)
  • Support Unicode file paths when loading an ONNX file (#5806)
  • Removed unused string_view include (#5813)
  • Use mac-release 10.15 (#5820)
  • Process subgraphs in inliner (#5841)
  • Enable unity(Jumbo) builds (#5768)
  • Print tensor dtypes as strings in shape inference (#5856)
  • Bump up IR_VERSION to 10 (#5860)
  • Support Python 3.12 (#5743)
  • Fix corner case where output size need to reduce by one in MaxPool (#5741)
  • Bump Numpy minimal version to 1.20 (#5902)
  • Fix endianness conversion in numpy_helper.to_array() (#5904)
  • Add valueinfos field to FunctionProto (#5903)
  • Remove deprecated properties from FormalParameter (#5921)
  • Add proto support for overloaded functions (#5011)
  • Add parser support for int4 types (#5934)
  • Update proto to add metadata props (#5938)
  • The latest Cmake 3.28.3 is failing with "Could NOT find Protobuf (missing: Protobuf_LIBRARIES)". Use Cmake 3.27.9 (#5951)
  • Fix ReferenceEvaluator when run from a subclass (#5936)

Documentation updates

  • Update top-k documentation (#5948)
  • Updated docs for DynamicQuantizeLinear to be consistent with reference implementation (#5603)
  • Clarify cond to If must contain a single element (#5617)
  • Update README.md (#5630)
  • Fix affineGrid doc error - output shape shall has no 'C' in it (#5648)
  • Use absolute link in README.md entirely (#5663)
  • [Doc clarification] Added unidirectional text for LayerNorm (#5686)
  • Add documentation for inliner (#5712)
  • update release doc for tag creation (#5721)
  • Doc: Add exception checks in check_model (#5736)
  • Add perm length constraint in Transpose doc (#5857)
  • Fix label encoder definition in schema (#5863)
  • Update batchnorm documentation (number of outputs for training mode) (#5932)
  • Q/DQ docs readability + 4bit info in onnx.proto (#5937)

Installation

You can upgrade to the latest release using pip install onnx --upgrade or build from source following the README instructions.

Contributors

Thanks to these individuals for their contributions in this release since last 1.16.0 release:
Aditya Goel, Adrian Lizarraga, Andreas Fehlner, Charles Volzka, Daniel Richard G, Danni, G. Ramalingam, Gal Hubara-Agam, Ilya Lavrenov, Justin Chu, Tabari Alexander, Takeshi Watanabe, WORLD PEACE, Wouter Deconinck, Xavier Dupré, Yuan Yao, dependabot[bot], galagam, jslap-ubi, liqun Fu

Loading

v1.15.0

31 Oct 17:04
@liqunfu liqunfu
v1.15.0
b86cc54
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.15.0

ONNX v1.15.0 is now available with exciting new features! We would like to thank everyone who contributed to this release! Please visit onnx.ai to learn more about ONNX and associated projects.

Key Updates

ai.onnx opset version increased to 20 with following changes:

  • New Operators (ai.onnx):

    • ImageDecoder a new ImageDecoder operator to be used in preprocessing models
    • RegexFullMatch a new operator for regex matching that is commonly used in feature preprocessing
    • StringConcat takes two string tensors as input and returns the elementwise concatenation of the strings in each tensor
    • StringSplit takes a string tensor as input and splits each element based on a delimiter attribute and a maxsplit attribute
    • AffineGrid Generates a 2D or 3D flow field (sampling grid), given a batch of affine matrices theta
    • Gelu applies gaussian error linear unit function or its approximation to input

  • Operator Updates (ai.onnx):

ai.onnx.ml opset version increased to 4 with following changes:

  • Operator Updates (ai.onnx.ml):
    • LabelEncoder adds keys_as_tensor and values_as_tensor attributes

New functionality:

  • Enable empty list of values as attribute PR#5559
  • Update diff bakend node tests for auto update doc PR#5604
  • Enable pylint checks with Ruff and remove pylint from lintrunner PR#5589
  • Getting onnx to treat inf/-inf as float literals. PR#5528
  • Create the onnxtxt serialization format PR#5524
  • Support JSON as a serialization target PR#5523
  • Support for parsing and printing empty list value as attribute PR#5516
  • Add auto update doc pipeline to help developers update docs PR#5450
  • Implement GELU as function op PR#5277
  • Integrate function-inlining with version-conversion PR#5211
  • Extend function type inference to handle missing optional parameters PR#5169
  • Create repr functions for OpSchema PR#5117
  • Utility to inline model-local functions PR#5105
  • Faster reference implementation for operator Conv based on im2col PR#5069
  • Support textproto as a serialization format PR#5112

ONNX now supports serializing to JSON, Text Proto as well as the ONNX Text Representation

Users are now able to serialize the model proto to a text format by specifying supported file extensions or supplying the format= argument in save_model.

For example

# model: onnx.ModelProto
onnx.save_model(model, "model.json")

will save the model as a json file.

Shape inference enhancements

  • [Spec] output_shape for ConvTranspose should not have batch and channels PR#5400
  • Infer rank where reshape shape is inferred PR#5327

Bug fixes and infrastructure improvements

  • Do not use LFS64 on non-glibc linu PR#5669
  • [Web] Use tensor_dtype_to_np_dtype instead of deprecated function PR#5593
  • Reject absolute path when saving external data PR#5566
  • Support Python editable builds PR#5558
  • Test onnxruntime 1.15 with opset 19/IR 9 and fix test source distribution PR#5376
  • Supports float 8 initializers in ReferenceEvaluator PR#5295
  • Fix check_tensor to work with large models on UNIX PR#5286
  • Fix check_tensor to work with large models on Windows PR#5227
  • Transpose scalar shape inference PR#5204
  • Enable RUFF as a formatter PR#5176
  • correct averagepool kernel shape in dilation test case PR#5158
  • Fix type constraints of Reshape(19) PR#5146
  • Add github action to check urls are valid PR#5434 Y
  • Introduce optional cpplint in CI PR#5396 Y
  • Test the serialization API with custom serializers PR#5315 Y
  • [CI] Use ONNX Hub directly in test_model_zoo CI PR#5267 Y
  • Clean up setup.py in favor of pyproject.toml PR#4879 Y

Documentation updates

  • Merge the two contributing docs and create instructions for updating an op PR#5584
  • [Doc] Update README.md regarding Protobuf update and fix typo in Slice-13 spec PR#5435
  • Generate both onnx and onnx-ml operator docs when ONNX_ML=1 PR#5381
  • Publish md files under docs/ to the documentation site PR#5312
  • Update OpSchema docs to include new methods and classes PR#5297
  • Fix missing examples in documentation for ai.onnx.ml PR#5228
  • Modify OneHot operator explanation PR#5197
  • Update CIPipelines.md PR#5157
  • Extend python API documentation PR#5156
  • Update sphinx to create markdown pages for operators PR#5137

Installation

You can upgrade to the latest release using pip install onnx --upgrade or build from source following the README instructions.

python setup.py develop deprecation

Direct invocation of setup.py is deprecated following https://setuptools.pypa.io/en/latest/deprecated/commands.html. To build ONNX, users should switch to use

# Editable installation
# Before: python setup.py develop
# Now
pip install -e .

# Build wheel
# Before: python setup.py bdist_wheel
# Now
pip install --upgrade build
python -m build .

Contributors

Thanks to these individuals for their contributions in this release sinc...

Read more

Contributors

take-cheeze, snnn, and 22 other contributors
Loading

v1.14.1

25 Aug 21:00
@yuanyao-nv yuanyao-nv
v1.14.1
1014f41
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.14.1

ONNX v1.14.1 is a patch release based on v1.14.1.

Bug fixes

  • Fix shape data propagation function to handle missing optional parameters #5219
  • Fix a couple of shape inference issues #5223
  • Extend function type inference to handle missing optional parameters #5169
  • Fix check_tensor to work with large models on Windows #5227
  • Fix check_tensor to work with large models on UNIX #5286
Loading