PyPI · #1019 most downloaded on PyPI

onnx

1.23.113M downloads/moonnx/onnx ↗New releases in your daily digest, changelog included.

Open Neural Network Exchange

Last release 5 days ago
29 Sep 2026
Release timing varies
gaps range from 8 days to 3 months
Nearly every release is documented
notes for 39 of 43 stable releases
Nothing withdrawn
no release was ever pulled
9 years old
54 releases · first in 2017

Release timeline

54 releases since 2017

2017201920212023

Releases

1.23.129 Sept 2026
This patch release includes important bug fixes to ONNX build.
This patch release includes important bug fixes to ONNX build.

What's Changed

Validate offset in save_external_data function PR Raised #8260

for Issue: #8260.

Full Changelog: v1.23.0...v1.23.1
Open source →
1.23.018 Sept 2026Breaking
Breaking Changes and Deprecations
ONNX v1.23.0 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.

What's Changed

IR Version 14

IR Version is changed from 13->14

Breaking Changes and Deprecations

perf(reference): vectorize Conv implementation by @justinchuby with @Copilot in #8366

Spec and Operator

New Operator SwiGLU is added [SwiGLU]

Fix Attention is_causal causal-mask alignment + composed is_causal/attn_mask NaN robustness for external (static) KV cache (#8054) by @titaiwangms in #8068

Add Celu-28 with float16/bfloat16/double support by @cyyever in #8107

docs: clarify Transpose operator spec by @pctablet505 in #8197

Add SwiGLU as a function-op by @gramalingam in #8202

Mark Range operator as deterministic by @take-cheeze in #8232

docs: fix ScatterND updates shape formula by @uditjainstjis in #8212

Add local_window_size attribute to Attention opset 25 by @FuZoe in #8108

Fix TensorScatter circular mode wrapping non-sequence coordinates by @justinchuby in #8353

Attention (opset 23/24): fix bf16 type mismatch in causal-mask and padding-mask paths by @justinchuby with @Copilot in #7840

feat: add FLOAT6E2M3 and FLOAT6E3M2 quantization data types by @andife in #8349

feat(defs): support bfloat16 in Compress and related ops by @justinchuby with @Copilot in #8078

Add mode attribute (DCR/CRD) to SpaceToDepth in opset 28, add function bodies to SpaceToDepth and DepthToSpace by @justinchuby with @Copilot in #7848

Allow float input to Mod when fmod=0 by @justinchuby with @Copilot in #7521

Add Einsum-28 with bfloat16 support by @mcollinswisc in #8313

refactor(defs): centralize shared schema docs by @justinchuby in #8387

Improve STFT operator documentation by @justinchuby with @Copilot in #7905

Add BitShift-28 with signed integer type support by @mcollinswisc in #8270

feat(defs): support all IR14 types in Optional ops by @youzow3 in #8176

fix(defs): restrict ReduceLogSum operators to float types in opset 28 by @malakazlan in #8384

RFC Proposal for Grouped MatMul operator by @gramalingam in #8193

Reference Implementation

Fix ScatterND reference impl for min/max with multi-axis indices by @Ankita7033 in #8099

Register latest QuantizeLinear and DequantizeLinear reference implementations by @napronald in #8182

Fix GatherElements output shape for empty indices by @kiwigitops in #8298

fix(reference): handle scalar NonZero inputs by @kiwigitops in #8296

Fix ReduceMax on empty boolean tensors by @kiwigitops in #8312

fix(reference): handle zero-length ReverseSequence slices by @kiwigitops in #8304

Support higher-rank ScatterElements evaluation by @kiwigitops in #8299

fix(reference): reject out-of-range Concat axes by @arcz in #8327

Runtime checks of shape annotations in reference evaluator by @gramalingam in #8307

fix(reference): use accurate exponential functions by @justinchuby with @Copilot in #8355

Utilities and Tools

Fix heap buffer over-read in Conv/Pool shape inference for weight rank mismatch by @titaiwangms with @Copilot in #8037

Fix make_attribute_ref to set ref_attr_name by @devin-lai in #8009

Address shape inference issues in Conv by @yuslepukhin in #8051

Fix annotated float attrs parsed from int literals by @fengjikui in #8065

Fix locale-dependent float parsing in C++ parser by @yuslepukhin in #8112

test: fix two copy-paste bugs that left code paths untested by @cyyever in #8159

Add loop test case with static loop bound by @gramalingam in #8146

Update shape inference tests to use parser by @gramalingam in #8168

Validate Scan num_scan_inputs to prevent shape-inference underflow by @cyyever in #8114

fix(version_converter): harden Scan adapters and domain-index lookup against malformed models by @andife in #8084

improve checker which fails on a particular mismatch between type and shape by @xadupre in #8211

Preserve inputs with no shape in Scan 8 -> 9 by @mcollinswisc in #8216

Fix OneHot shape inference when depth is empty by @cbourjau in #8177

Add Resize 18 to 17 version converter adapter by @napronald in #8209

Update hasInput and hasOutput methods of InferenceContextImpl by @gramalingam in #8271

Fix shape inference overflow by @andife in #8277

fix(shape_inference): handle missing function inputs in subgraphs by @arcz in #8305

fix(shape_inference): prevent use-after-scope during function inference by @arcz in #8303

fix(shape_inference): reject zero scalar SplitToSequence split by @arcz in #8322

fix(shape_inference): bound inferred rank materialization by @arcz in #8321

fix(version_converter): prevent initializer-name use-after-free by @arcz in #8334

fix: guard ExtendSupportedTypes against missing output in version converter by @andife in #8274

fix(version_converter): validate Captured node outputs by @arcz in #8329

fix(shape_inference): validate TreeEnsemble leaf weight rank by @arcz in #8336

Update shape inference test to use check type option by @gramalingam in #8323

fix(version_converter): validate Reshape output in Softmax downgrade by @arcz in #8326

fix(shape_inference): prevent use-after-scope during node inference by @arcz in #8330

fix(inliner): handle Constant nodes without outputs by @arcz in #8325

fix(checker): reject non-canonical FLOAT6 encodings by @justinchuby in #8386

fix(shape_inference): reject Split nodes with no outputs by @arcz in #8328

Build, CI and Tests

Update renovate config for Pixi lock file update by @cbourjau in #8022

Remove redundant min-deps tests in release process by @cbourjau in #8034

Replace windows-latest with windows-2022 to fix CI by @cbourjau in #8074

Update screenshot with correct configuration by @cbourjau in #8073

Use a cache for the link checker by @cbourjau in #8098

Clean-up tests by @cbourjau in #8154

Fix pyodide/emscripten CMake configure after nanobind 2.13.0 bump by @andife in #8157

Fix Python test bugs by @cyyever in #8160

Migrate to pytest's asserts by @cbourjau in #8155

Bump protobuf/abseil-cpp versions used to build protobuf from source in CI by @andife in #8172

Build Pyodide wheel for Python 3.14 by @metalmancode in #8192

Add Pad shape inference coverage for value_ints by @nightcityblade in #8206

Remove submodules option from checkout step by @andife in #8226

fix(common): route tensor dim errors through throw_tensor_error by @rvandermeulen in #8220

ci: add Linux GCC/Clang build with exceptions disabled by @andife in #8225

Add TSAN and TypeSAN sanitizer support; fix ASAN CI env-var propagation by @cyyever in #7471

Remove node test artifacts by @cbourjau in #7959

Add tests for direction attribute of RNN ops by @mcollinswisc in #7935

Fix b_zero_point for int8 in QLinearMatMul 3D test case by @andife with @Copilot in #7991

Fix Unique backend test output shapes by @DarkBall123 in #8180

Precut Version Update for Release 1.23.0 by @sfatimar in #8368

ci: add a clang-cl Windows job to catch MSVC-only permissive extensions by @andife in #8280

Pin ml_dtypes==0.5.4 in numpy<2.0 CI test jobs by @andife in #8378

Documentation

Add ROADMAP.md: 12-month roadmap template for SIGs and Working Groups by @andife in #8030

Expand roadmap with SIG details for 2026-2027 by @andife in #8059

Update operator sig roadmap by @gramalingam in #8070

Add C-API definition to roadmap by @cbourjau in #8097

Bump version number to 1.23.0 by @andife in #8102

Add jax2onnx to converter documentation by @enpasos in #8103

Update ROADMAP.md by @andife in #8120

fix calender link description (working-groups.md) by @andife in #7663

Remove onnx.tools.net_drawer from repository by @andife in #8129

docs: Refresh CONTRIBUTING/README docs and move Model Zoo links to Hugging Face by @andife in #8123

docs: update release tracking docs for the 1.22.0 release by @andife in #8190

docs: recommend Conventional Commits for agent-authored PR titles by @andife in #8188

docs: add REUSE annotation for AGENTS.md symlink by @andife in #8224

Update RELEASE-MANAGEMENT.md by @andife in #8234

docs: correct model validation assurances by @andife in #8276

docs: fix cross-platform environment variable syntax by @andife in #8283

docs: require labels on agent-authored PRs by @andife in #8285

docs: correct Protobuf build version guidance by @andife in #8286

Fix warnings from docs-build and ensure we fail on warnings in the future by @cbourjau in #8294

docs: refresh community governance docs, add History section by @andife in #8297

docs: clarify release and reproducibility guidance by @andife in #8284

docs: clarify spurious unknown variable in 'Slice' operator by @BW-SK in #8335

test: fix typo flagged by the typos lint hook by @cyyever in #8339

docs(community): add GitHub Organization Seat Policy by @andife in #8223

fix(docs): restore operator examples by @kiwigitops in #8332

docs: add llms.txt for AI-agent discoverability by @andife in #8348

Update RELEASE-MANAGEMENT.md by @sfatimar in #8406

Version change to rc1 by @sfatimar in #8407

Version changed to 1.23.0 by @sfatimar in #8469

Full Changelog: v1.22.0...v1.23.0

1.22.015 Jun 2026Breaking

Breaking Changes and Deprecations

ONNX v1.22.0 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.

What's Changed

Breaking Changes and Deprecations

Swap qk_matmul_output_mode 1 & 2 to match computation order by @titaiwangms in #7913

Spec and Operator

Two new operators LinearAttention-27 and CausalConvWithState-27 were introduced.

Fix number of pad modes in doc_strings.cc by @assafpr in #7803
Add FlexAttention Op to ai.onnx.preview opset by @mshr-h in #7534
Fix Attention op softcap ordering: apply before mask/bias by @titaiwangms in #7867
Add LinearAttention and CausalConvWithState operators (Opset 27) by @tadani3 in #7950
feat(generator): extend Range operator with float16 and bfloat16 support (opset 27) by @andife in #7923

Reference Implementation

Fix missing 'mul' reduction in ScatterElements reference implementation by @zdryan in #7842
Fix QLinearMatMul output saturation by @karimbaidar in #7868
Fixed more bugs in the Scan reference op by @tadani3 in #7964

Utilities and Tools

Fix Slice shape inference crashes with SIGABRT on empty dimensions by @titaiwangms in #7738
Rename misleading input_rank param to input_dim_value in processSlice… by @titaiwangms in #7739
fix: Conv/Pool strides validation by @edgchen1 in #7764
fix: add input/output bounds checks in version converter adapter by @andife in #7813
Harden version conversion against malformed inputs by @andife in #7872
fix: add input rank checks in Gemm version converter adapters by @andife in #7880
Fix raw_data handling in version converter adapters by @cyyever in #7910
Fix checker to use len() instead of sys.getsizeof() for protobuf size check by @OmarAzizi in #7760
Add version macros by @cbourjau in #7918
Remove internal spec_to_yaml tool by @cbourjau in #7985
Address shape inference shortcomings by @yuslepukhin in #7997
Add unifyInputShape / unifyInputShapePrefix shape inference utilities by @gramalingam in #7999
Add operator+ and operator- for Dim by @gramalingam in #8000
Fix KeepAspectRatioHelper precision for scaled output dimensions by @elwhyjay in #8007
Fix heap buffer over-read in Conv/Pool shape inference for weight rank mismatch by @Copilot in #8037

Build, CI and Tests

Add update into main.yml by @titaiwangms in #7687
Update check_urls.yml by @andife in #7716
Update add_msvc_runtime_flag to work with MSVC_RUNTIME_LIBRARY by @Shadows-of-Fire in #7660
Try to fix renovate by @andife in #7742
fix upload; Update release_win.yml by @andife in #7728
Allow release CIs to run when a labeled PR receives new commits by @Copilot in #7741
Update pixi.{toml,lock} by @cbourjau in #7746
hash for googletest by @andife in #7765
Update RELEASE-MANAGEMENT.md by @andife in #7773
Update doc CIPipeline by @andife in #7782
use reviewdog to fix the pr_checks workflow by @andife in #7780
Update copilot-setup-steps.yml; persist-credentials: false by @andife in #7768
Update release_linux.yml; replace tag by hash by @andife in #7769
Fix pipeline src preview by @andife in #7787
Bump protobuf to v33.6 by @cyyever in #7517
fix pr_checks_post.yml by using the correct reporter in reviewdog by @andife in #7789
Skip very slow Python tests on Windows debug builds by @cbourjau in #7819
Fix cross-platform date command in CMakeLists.txt by @Chessing234 in #7816
Modify URL checker workflow permissions and action by @andife in #7832
fix additional input in workflow by @andife in #7834
fix: suppress unused-parameter warnings in try_kernel_contained_open by @andife in #7849
Pin GitHub Actions to immutable commit SHAs by @andife in #7852
Add wheels for Pyodide by @andife in #7847
Improve CodeQL config by @cyyever in #7870
integrate check-wheel-contents in CI workflows by @andife in #7846
feat: embed CycloneDX SBOM in wheel per PEP 770 by @andife in #7861
Fix CI link-checker issues by @cbourjau in #7909
fix: only download artifacts on workflow_dispatch in publish_release_build_to_pypi by @andife in #7912
topic: Allow overriding cmake build directory via environment variable by @WithEnoughCoffee in #7915
Ignore blocked links by @cbourjau in #7919
chore: improve Renovate config — cooldown, correct label, PR notes by @andife in #7922
Fix link-checker CI by @cbourjau in #7924
Update Python version matrix in release workflow; skip 3.13t for a gr… by @andife in #7932
Update Python versions in release workflow (remove 3.13t from testing) by @andife in #7934
Remove cpplint (superseded by clang-tidy) by @cbourjau in #7942
Add hard-failing zizmor lint and fix existing issues by @cbourjau in #7941
Remove redundant reuse-action by @cbourjau in #7943
Fix links (and thus CI error) by @cbourjau in #7946
CI: add labeled SLSA provenance test path and harden checkout credentials by @andife in #7951
Remove submodules option from lint workflow by @andife in #7958
Use cibuildwheel for all releases by @cbourjau in #7901
Fix generated md files by @cbourjau in #7973
Use Renovate to update pixi lock file once a month by @cbourjau in #7980
fix: revert accidental protobuf v33.6 bump and remove requirements-release_build.txt by @andife in #7982
Run pip check to validate consistency of pyproject-dependencies with environment by @cbourjau in #7960
Build correct pyemscripten wheel for PyPI by @cbourjau in #7998
Use same 25.1 protobuf for all releases and simplify sbom creation by @cbourjau in #7995
fix: prevent cmake parallel build race in proto generation by @andife in #8003
fix: correct argument order in ONNX_OPERATOR_SET_SCHEMA_DEBUG_VARIABLE macro call by @andife in #8004
Enable MSVC warnings by @justinchuby in #7562
Fix/sdist missing SBOM cdx json by @andife in #8010
Follow up for scikit-build-core migration by @take-cheeze in #8017
Run lints also on Windows by @cbourjau in #8014
Fix xcode build by @cbourjau in #8056

Documentation

bump VERSION_NUMBER in main branch by @Sunny-Anand in #7712
remove link for check_urls action by @Sunny-Anand in #7713
bump version for defs operator and schema after main version bump by @Sunny-Anand in #7715
Add Security Assurance Case document by @andife in #7679
Add CLAUDE.md with project guidelines for Claude Code by @cyyever in #7666
Update RELEASE-MANAGEMENT.md by @andife in #7762
Update RELEASE-MANAGEMENT.md by @andife in #7774
Fix documentation typos and grammar errors in API docs by @Chessing234 in #7809
Add ONNX Incident Response Plan document by @andife in #7830
Add skill files for new op, op updates, function body definition, type and shape inference by @gramalingam in #7878
Fix reuse by @andife in #7899
Execute code snippets in PythonAPIOverview.md (+ fixes) by @cbourjau in #7856
Extend release compatibility matrix back to ONNX 1.10 by @andife in #7929
Update RELEASE-MANAGEMENT.md by @andife in #7976
Update RELEASE-MANAGEMENT.md by @andife in #7977
Render literal < in Cast FLOAT8E8M0 docs table by @Copilot in #7936
Fix escaped default attribute values in generated operator docs by @Copilot in #8002

Other Changes

Improve external data file handling by @titaiwangms in #7686
Extend parser/printer to support quoted strings as symbolic dims by @Copilot in #7699
Improve external data file handling - onnx.load by @titaiwangms in #7717
docs: fix window size type constraint wording by @tsubasakong in #7719
Improve spec_to_yaml.py by @cyyever in #7734
Enhance ONNX_HARDENING with OpenSSF-recommended compiler flags by @cyyever in #7724
Fix various issues by @cyyever in #7737
Enable more ruff rules by @cyyever in #7748
Merged Fix object state corruption and DoS via ExternalDataInfo attribute injection by @titaiwangms in #7751
Update SECURITY.md by @andife in #7779
Fix formatting in RELEASE-MANAGEMENT.md by @andife in #7781
Rename docs to match PascalCase by @andife in #7778
Remove the autoupdate doc workflow by @cbourjau in #7785
Fix test_adam_multiple missing epsilon attribute in model.onnx by @Krishnachaitanyakc in #7763
Fix np.prod integer overflow on numpy < 2.0 by using dtype=np.int64 by @cyyever in #7783
Fix TOCTOU race in external data file open by @cyyever in #7790
Fix nanobind arg name by @cbourjau in #7823
Fix various linting issues and broken links by @cbourjau in #7826
Add Pixi task for building docs from locked environment by @cbourjau in #7824
Update Docker image version for x86_64 wheel build by @andife in #7804
Update CMakeLists.txt; update nanobind to 2.12.0 by @andife in #7851
Build docs on CI using Pixi by @cbourjau in #7845
Extend renovate config: track googletest releases with hash and auto-label PRs by @andife in #7853
improve codeql by @andife in #7863
Improve test matrix (e.g. fix unity build) by @cbourjau in #7860
Remove non-functional and insecure split-workflow CI pairs by @andife in #7876
Normalize legacy helper names to explicit opset ranges by @andife in #7873
fix: detect cycles in model-local functions to prevent stack overflow (GHSA-7w46-vvrh-m8q5) by @cyyever in #7815
Add pre-commit hooks by @cbourjau in #7857
Apply ruff formatting by @cbourjau in #7908
Remove deduplicated helpers by @cyyever in #7907
fix: add rank check in RNNShapeInference_opset1_to_6 to prevent OOB read by @andife in #7879
Drop redundant semicolons in macros by @cyyever in #7911
Fix wrong mantissa mask in to_float8e8m0 round-up mode by

Note truncated.

Open source →

1.21.027 Mar 2026Security

Revise security vulnerability reporting guidelines by @andife in #7674

ONNX v1.21.0 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.

What's Changed

Breaking Changes and Deprecations

Remove defunct model hub integration by @andife in #7678

Spec and Operator

Revert opset 25 version bump by @titaiwangms in #7441
Add 2 bit support to onnx by @vraspar in #7446
Bump opset version to 26 by @titaiwangms in #7469
Remove enforcement to node determinism attribute by @titaiwangms in #7473
Export functions by @cyyever in #7505
[Reland] Cumulative Product Operator by @titaiwangms in #7400
Fix Div integer semantics to use trunc division by @MagellaX in #7585
Clarify DFT behavior when inverse=True and onesided=True (irfft) by @simonbyrne in #7574
Specify 0/0 case in LpNormalization by @titaiwangms in #7618
Clarify NonMaxSuppression IoU threshold uses strict comparison by @Copilot in #7619
Relax model domain requirement from MUST to SHOULD by @Copilot in #7668
Add BitCast operator for bitwise type reinterpretation by @Copilot in #7527

Reference Implementation

Fix CenterCropPad: compare target shape with dimension, not axis index by @Copilot in #7522
Vectorize sigmoid op implementation by @justinchuby in #7556
Fixing verbose logging error at verbose=3 for reference_evaluator by @rothej in #7597
Clean up reference evaluator tests by @VedantMadane in #7684

Utilities and Tools

Add version check for test_executable_permission_check by @andife in #7511
Fix index out of bounds in version converter adapters by @rothej in #7493
Fix default attribute values in shape inference by @matteosal in #7602
Fix Softmax-family shape inference for scalar inputs by @MagellaX in #7625
Fix/merge models value info by @MagellaX in #7608
Add version converter adapters for opset 15, 16, 17, 18 by @alexkvitkevich in #7677
shape_inference: Validate expected size of scalar tensor in ParseData by @skottmckay in #7675

Build, CI and Tests

Force labels in PRs by @titaiwangms in #7442
Fix reuse by @andife in #7463
Change precedence from 'aggregate' to 'override' for generating scripts by @andife in #7458
a) 3.14-dev -> 3.14, b) reduce template injection thread by @andife in #7461
Export register functions by @cyyever in #7496
Fix Python executable detection in virtual environments by @aoguntayo in #7485
Merged Release Workflows for Windows by @Raghul-M in #7509
Bump nanobind to 2.10.2 by @cyyever in #7479
Fix freebsd build by @cyyever in #7518
Revert ONNX CMake changes by @cyyever in #7515
Export functions used in PyTorch by @cyyever in #7524
Export protobuf symbols by @cyyever in #7525
Fix CMAKE_ARGS parsing for windows compatibility by @hmaarrfk in #7532
Replace deprecated github action "test-results-action" by @andife in #7552
Wheels for python 3.14t by @andife in #7558
Clarify permissions comment and update dependencies install by @andife in #7577
Disable credential persistence in checkout action by @andife in #7578
Update create_release.yml, different label options by @andife in #7081
Fix "code injection via template expansion" (build mode in workflow) by @andife in #7584
Add GitHub Actions workflow for dependency review by @andife in #7579
Simplify conditions in workflow by @andife in #7588
Add renovate for updating docker images by @andife in #7572
CMake: improve nanobind discovery for offline builds by @MagellaX in #7530
Build option for OpenSSF Compiler Hardening Flags by @andife in #7601
Improve debugging for pr_checks by @andife in #7623
Fixes pr checks by @andife in #7630
improve condition in github workflows by @andife in #7658
Add ONNX_INSTALL option to disable CMake installations by @Shadows-of-Fire in #7653
fix windows build ; upload by @andife in #7727
Update VERSION_NUMBER to rc4 by @andife in #7759
Update VERSION_NUMBER to final release version by @andife in #7772

Documentation

Update RELEASE-MANAGEMENT.md (time for release cut 1.21) by @andife in #7466
Update rc version publish process by @andife in #7440
Fix typos by @cyyever in #7478
Clarify numpy version dependencies in requirements by @andife in #7488
Add license information to check_pr_label.yml by @andife in #7489
Deduplicate operator doc strings to reduce binary size by @MagellaX in #7531
Clean up reference evaluator tests (#7098) by @sumit2303 in #7654
fix wrong cmake version in Update RELEASE-MANAGEMENT.md by @andife in #7662
Revise security vulnerability reporting guidelines by @andife in #7674
update version in main for next release and also add missing version … by @Sunny-Anand in #7680
[Cherry-Pick] Merge commits from main for security fixes by @Sunny-Anand in #7688
update release branch version to 1.21.0rc1 by @Sunny-Anand in #7714
Cherry pick commits into the release branch by @Sunny-Anand in #7718
update release to rc2 by @Sunny-Anand in #7732
Cherry pick commit by @Sunny-Anand in #7740
update version to rc3 by @Sunny-Anand in #7743

Other Changes

Bump main to v1.21.0 by @titaiwangms in #7437
Bump ruff from 0.13.3 to 0.14.3 by @dependabot[bot] in #7447
Bump actions/github-script from 7 to 8 by @dependabot[bot] in #7452
Bump actions/upload-artifact from 4.6.2 to 5.0.0 by @dependabot[bot] in #7457
Bump actions/download-artifact from 5.0.0 to 6.0.0 by @dependabot[bot] in #7451
Bump reviewdog/action-cpplint from 1.10.0 to 1.11.0 by @dependabot[bot] in #7456
Bump reviewdog/action-misspell from 1.26.3 to 1.27.0 by @dependabot[bot] in #7449
Bump prefix-dev/setup-pixi from 0.9.1 to 0.9.2 by @dependabot[bot] in #7455
Bump editorconfig-checker from 3.4.0 to 3.4.1 by @dependabot[bot] in #7448
Bump stefanzweifel/git-auto-commit-action from 6.0.1 to 7.0.0 by @dependabot[bot] in #7450
Bump fsfe/reuse-action from 5.0.0 to 6.0.0 by @dependabot[bot] in #7453
Bump github/codeql-action from 3.30.6 to 4.31.2 by @dependabot[bot] in #7454
supply chain security => adapt dependabot.yml by @andife in #7459
Add persist-credentials option to checkout action by @andife in #7460
Enable conversion from DataTypeSet into set[str] by @cyyever in #7481
Update entrypoint.sh for improved syntax and checks by @andife in #7483
Require ml_dtypes>=0.5.4 on s390x by @stliibm in #7484
Fix cpplint warnings by @cyyever in #7482
Remove empty line from requirements.txt by @andife in #7492
Add copyright and SPDX license to workflow by @andife in #7490
Bump ruff from 0.14.3 to 0.14.6 by @dependabot[bot] in #7501
Bump actions/checkout from 5.0.0 to 6.0.0 by @dependabot[bot] in #7500
Bump zizmorcore/zizmor-action from 0.2.0 to 0.3.0 by @dependabot[bot] in #7499
Bump ZedThree/clang-tidy-review from 0.21.0 to 0.22.2 by @dependabot[bot] in #7497
Bump clang-format from 21.1.2 to 21.1.6 by @dependabot[bot] in #7503
Bump types-protobuf from 6.30.2.20250822 to 6.32.1.20250918 by @dependabot[bot] in #7353
Add sanity checks for CLI arguments in entrypoint.sh by @andife in #7491
Bump prefix-dev/setup-pixi from 0.9.2 to 0.9.3 by @dependabot[bot] in #7498
Add a tool to dump ONNX schema into yaml files by @cyyever in #7480
More clang-tidy fixes by @cyyever in #7486
Bump actions/checkout from 6.0.0 to 6.0.1 by @dependabot[bot] in #7542
Bump actions/stale from 10.1.0 to 10.1.1 by @dependabot[bot] in #7545
Bump github/codeql-action from 4.31.2 to 4.31.9 by @dependabot[bot] in #7543
Bump actions/upload-artifact from 5.0.0 to 6.0.0 by @dependabot[bot] in #7548
Bump actions/download-artifact from 6.0.0 to 7.0.0 by @dependabot[bot] in #7541
Bump actions/setup-python from 6.0.0 to 6.1.0 by @dependabot[bot] in #7547
Bump codecov/codecov-action from 5.5.1 to 5.5.2 by @dependabot[bot] in #7544
Bump ZedThree/clang-tidy-review from 0.22.2 to 0.22.3 by @dependabot[bot] in #7546
Bump stefanzweifel/git-auto-commit-action from 7.0.0 to 7.1.0 by @dependabot[bot] in #7549
Bump mypy from 1.18.2 to 1.19.1 by @dependabot[bot] in #7540
Bump clang-format from 21.1.6 to 21.1.8 by @dependabot[bot] in #7538
Bump ruff from 0.14.6 to 0.14.10 by @dependabot[bot] in #7537
remove cpplint rule "-readability/todo" from lint.yml by @andife in #7554
Fix cpplint copyright warnings by @andife in #7553
Update pixi.lock file by @cbourjau in #7555
Update RELEASE-MANAGEMENT.md by @andife in #7559
fix possible "code injection via template expansion" by @andife in #7576
More tidy fixes by @cyyever in #7519
Fix zizmor findings by @andife in #7581
Improve lint and cpplint fixes by @andife in #7583
Create release-verification.md by @andife in #7595
Update renovate config by @andife in #7600
Keep non-tensor type information in IR by @take-cheeze in #7592
Fix create_releases.yml by @andife in #7605
Ignore .pb files from github language classification by @justinchuby in #7606
lint copyright header by @andife in #7611
IR: Add API to generate unique name for consistency by @take-cheeze in

Note truncated.

Open source →

1.20.01 Dec 2025Breaking

Breaking Changes and Deprecations

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)

Open source →

1.19.027 Aug 2025Breaking

Breaking Changes and Deprecations

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

Deprecate printable_graph in helper by @justinchuby in #6803
Remove deprecated mapping constants by @justinchuby in #6914
Remove re2 dependency by @cbourjau in #7083
Use ml_dtypes everywhere by @justinchuby in #7089

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

Fix Resize reference operator by @xadupre in #7105
fixed erf for empty inputs by @konstantin-pueckler-qc in #7170
Fix Softmax reference for inputs of length 1 by @konstantin-pueckler-qc in #7169
Fix return type of HardSigmoid in reference implementation by @konstantin-pueckler-qc in #7168
Fix hardmax reference implementation by @konstantin-pueckler-qc in #7167
[Reference] Fix constant of shape when input value is 0d by @justinchuby in #7177

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

Use ONNX_WERROR=ON in all jobs by @cyyever in #6825
Cleanup CMake scripts by @cyyever in #6828
Better support of sanitizers by @cyyever in #6826
Remove the pull trigger in source dist test by @justinchuby in #6861
Use CONFIG to find protobuf by @ktf in #6840
Update to checkout submodules properly by @justinchuby in #6884
Improve lint CI by @justinchuby in #6899
Remove win arm64 from main.yml by @andife in #6906
Enhance Build Process and CI Configuration (combine pipelines) by @andife in #6926
Update and rename Install_test.yml to install_test.yml by @andife in #6950
Update CMake to 3.24 and use LINK_LIBRARY:WHOLE_ARCHIVE by @cyyever in #6934
replace requirements_release with requirements_release_build in codeql.yml by @andife in #6958
Add backend node testing for Lpnormalization op by @jagadeeshvx in #6997
Refine pybind11 integration by @cyyever in #7024
Use pybind11_add_module by @cyyever in #7034
Update input and output tensors in pb files to match the model by @amarin16 in #7074
Generate the test data that should be in the repo but was omitted by @justinchuby in #7099
Fix cast test cases by @justinchuby in #7102
Test ArgMax with multiple maximal values and select_last_index = 0 by @meilofveeningen-rl in #7104
Add more test cases with attention by @xadupre in #7117
Update CMakeLists.txt to prevent ICE protobuf failure by @justinchuby in #7121
Fix shared module name when cross-compiling by @zboszor in #7026
Add missing symbols for onnx-mlir by @Sunny-Anand in #7179
improve condition in create_release.yml by @andife in #7196

Documentation

Update CIPipelines.md by @justinchuby in #6885
Update IRv10 brief docs by @justinchuby in #6963
Fix some typos in documentation by @bentheiii in #7156
[Docs] Add tip blocks referencing ir-py project for Python APIs by @Copilot in #7109

Other Changes

Merge Windows CI jobs by @cyyever in #6827
Improve source build testing by @andife in #6831
use HEAD_SHA instead of HEAD_REF in auto_update_doc.yml by @mshudrak in #6809
Fix clang-tidy warnings by @cyyever in #6832
Update pypa / manylinux2014_x86_64 in release_linux_x86_64.yml to 2025.03.22-2 by @andife in #6833
Fix the ONNX_BUILD_CUSTOM_PROTOBUF bug introduced by PR#6495. by @cainbit in #6830
Bump protobuf to v30.1 by @cyyever in #6804
Remove onnx/onnx-data_pb.h by @cyyever in #6836
replace quansight-labs/setup-python with actions/setup-python by @ngoldbaum in #6837
integrate release_mac_freethreading into release_mac by @andife in #6841
Bump protobuf to v30.2 by @cyyever in #6839
Improve pyproject.toml and add py.typed by @cyyever in #6843
Bump ruff to 0.11 and types-protobuf to 5.29.1.20250315 by @cyyever in #6846
Bump actions/setup-python from 5.4.0 to 5.5.0 by @dependabot[bot] in #6853
Bump actions/upload-artifact from 4.6.1 to 4.6.2 by @dependabot[bot] in #6852
Bump actions/download-artifact from 4.1.9 to 4.2.1 by @dependabot[bot] in #6856
Bump clang-format to 20 by @cyyever in #6850
Fix external data bug in version converter by @yuanyao-nv in #6847
Bump github/codeql-action from 3.28.11 to 3.28.13 by @dependabot[bot] in #6858
Bump editorconfig-checker from 3.2.0 to 3.2.1 by @dependabot[bot] in #6860
Bump reviewdog/action-misspell from 1.26.1 to 1.26.3 by @dependabot[bot] in #6857
Bump reviewdog/action-shellcheck from 1.29.0 to 1.30.0 by @dependabot[bot] in #6854
Added selection option to enable both release and preview builds in the create_release.yml workflow by @andife in #6851
Add Publishing Workflow for onnx to Test PyPI (https://test.pypi.org/project/onnx/) by @andife in #6849
Bump reviewdog/action-cpplint from 1.8.0 to 1.9.2 by @dependabot[bot] in #6855
Remove pyi generators by @yadunand-kamath in #6863
Update win_no_exception_ci.yml by @andife in #6872
remove not used condition in preview_source_dist_test.yml by @andife in #6873
Update OnnxReleases.md by @andife in #6871
Remove ipython, twine from requirements*.txt by @andife in #6874
Update release_linux_aarch64.yml by @andife in #6876
Update and rename release_win.yml to release_win_x86_64.yml by @andife in #6875
remove jupyter from requirements-dev.txt by @andife in #6878
Remove outdated comments in clang-tidy config by @cyyever in #6882
Use std::filesystem to simplify code by @cyyever in #6402
Add support for Free-Threading in Linux Wheel Builds by @andife in #6835
Integrate freethreading parts from separate file into main by @andife in #6889
Update VERSION_NUMBER to 1.19 by @andife in #6890
Update versioning in the main branch after release branch cut by @andife in #6892
Link privately to protobuf static libraries by @cyyever in #6881
Update release_linux_aarch64 to include 3.13t by @andife in #6893
Remove nbval dependency, replaces #6896 by @xadupre in #6897
Consolidate Freethreading Requirements into Main Requirements Files for Enhanced Tooling by @cyyever in #6844
Delete pyproject_pylint.toml by @justinchuby in #6903
Add native ARM64 Windows Builds by @andife in #6904
reduce length of names in create_release.yml by @andife in #6909
better condition and explanations in create_release.yml by @andife in #6910
Add workflow dispatch option to publish whl to pypi onnx by @andife in #6819
Update and rename release_win_freethreading.yml to release_win_x64_fr… by @andife in #6911
Use Native Runner für linux Aarch64 whl (public preview runner available) by @andife in #6907
Export symbols used by PyTorch by @cyyever in #6915
Export more symbols used by PyTorch by @cyyever in #6916
Use Python3::Interpreter instead of Python3_EXECUTABLE by @cyyever in #6918
Simplify CMake code by @cyyever in #6927
Define PYBIND11_DETAILED_ERROR_MESSAGES by @justinchuby in #6929
Bump ruff from 0.11.2 to 0.11.8 by @dependabot[bot] in #6937
Bump actions/setup-python from 5.5.0 to 5.6.0 by @dependabot[bot] in #6940
Bump actions/download-artifact from 4.1.9 to 4.3.0 by @dependabot[bot] in #6939
Bump types-protobuf from 5.29.1.20250315 to 5.29.1.20250403 by @dependabot[bot] in #6938
Bump github/codeql-action from 3.28.13 to 3.28.16 by @dependabot[bot] in

Note truncated.

Open source →

onnx

Release timeline

Releases

What's Changed

What's Changed

IR Version 14

Breaking Changes and Deprecations

Spec and Operator

Reference Implementation

Utilities and Tools

Build, CI and Tests

Documentation

What's Changed

Breaking Changes and Deprecations

Spec and Operator

Reference Implementation

Utilities and Tools

Build, CI and Tests

Documentation

Other Changes

What's Changed

Breaking Changes and Deprecations

Spec and Operator

Reference Implementation

Utilities and Tools

Build, CI and Tests

Documentation

Other Changes

What's Changed

Commits

Updated Op list:

Key Updates:

Breaking Changes and Deprecations

Spec and Operator

Reference Implementation

Utilities and Tools

Build, CI and Tests

Documentation

All changes

Key Updates

IR Version 12

ai.onnx Opset 24

Other

What's Changed

Breaking Changes and Deprecations

Spec and Operator

Reference Implementation

Utilities and Tools

Build, CI and Tests

Documentation

Other Changes