v0.5.2

What's Changed

Optimizer and rewriter

• [rewriter] Remove generic pattern matcher by @justinchuby in #2567
• Add GQA fusion to ONNX fusions by @gramalingam in #2524

Torch Lib

• [torchlib] Fix aten_gather to correctly handle scalar indices by @linshokaku in #2566
• [torchlib] Simplify linalg_vector_norm to remove the redundant Abs by @justinchuby in #2570

New Contributors

• @linshokaku made their first contribution in #2566

Full Changelog: v0.5.1...v0.5.2

v0.5.1

What's Changed

Optimizer and rewriter

• Remove CheckerPass from ort_fusion by @justinchuby in #2560

Other Changes

• Bump version from 0.5.0 to 0.5.1 by @justinchuby in #2559
• Use ir.val to replace ir.Input by @justinchuby in #2556
• chore(deps): bump ruff from 0.12.11 to 0.13.0 in /requirements/lintrunner by @dependabot[bot] in #2563

Full Changelog: v0.5.0...v0.5.1

v0.5.0

What's Changed

Breaking Changes

• Refactor rewrite rules into the rewriter.rules namespace by @justinchuby in #2531
• Update constant folding behavior for large tensors by @justinchuby in #2488

Optimizer and rewriter

• [Rewriter] Prevent out of range when matching node outputs by @iksnagreb in #2508
• Add RMS Normalization variant by @gramalingam in #2519
• [Optimizer] Fix reinterpretation of strings in _get_numpy_value by @iksnagreb in #2514
• Improve symbolic dim tracking by @gramalingam in #2520
• Remove function extraction in ONNX rotary embedding by @gramalingam in #2525
• [Optimizer] Avoid accessing None value in _process_constant_node by @iksnagreb in #2513
• Increase DEFAULT_CONSTANT_FOLD_INPUT_SIZE_LIMIT by @justinchuby in #2527
• [Rewriter(matmul_add_to_gemm)]: check shapes by @AyoubMDL in #2528
• Add ort-specific passes to ort_fusion by @titaiwangms in #2532
• [Reland] Update SplitToSequence in constant folding by @titaiwangms in #2544
• [Rewriter]: add fusion rules for successive Min/Max patterns by @AyoubMDL in #2500
• [rewriter] Unify reshape flatten ops by @Johansmm in #2518
• Do not try to fold op.SplitToSequence when split is None by @titaiwangms in #2550
• [Rewriter] Add fuse batchnorm to default rules by @AyoubMDL in #2553
• Add Conv-Affine(Mul+Add) and hardswish fusion by @Stonesjtu in #2472
• Fix rewriter and CI tests for the latest onnx-ir version by @justinchuby in #2554

Torch Lib

• [torchlib] Modify aten_unbind to use None for split_sizes by @justinchuby in #2536
• [torchlib] Improve pixel_shuffle by @justinchuby in #2537
• [torchlib] Improve handling of SymInt[] by @justinchuby in #2522
• [torch] Fix incorrect Concat when processing dynamic paddings by @kistenklaus in #2540
• Add test for dynamic padding by @justinchuby in #2541
• [torchlib] Mark atan2 as trace_only and map NaN to 0 by @justinchuby in #2557
• [torchlib] Fix repeat_interleave when repeats is a symbolic tensor by @xadupre in #2548
• Support enable_gqa and only support 4D Q, K, and V by @titaiwangms in #2558
• [torchlib] Implement torch.ops.prims.broadcast_in_dim.default by @Copilot in #2382

Other Changes

• chore(deps): bump actions/upload-pages-artifact from 3 to 4 by @dependabot[bot] in #2517
• Generate opset24 ops by @justinchuby in #2523
• Disable unstable tests by @xadupre in #2512
• Bump version to 0.4.1 by @justinchuby in #2529
• More robust checks for FLOAT8E8M0 by @justinchuby in #2530
• chore(deps): bump ruff from 0.12.10 to 0.12.11 in /requirements/lintrunner by @dependabot[bot] in #2535
• Implements repeat_interleave by @xadupre in #2477
• Update onnx-weekly version to 1.20.0 by @justinchuby in #2545
• [Rewriter] Support specifying node name in rewrites by @AyoubMDL in #2474
• Bump version to 0.5.0 by @justinchuby in #2538

New Contributors

• @iksnagreb made their first contribution in #2508
• @kistenklaus made their first contribution in #2540
• @Stonesjtu made their first contribution in #2472

Full Changelog: v0.4.0...v0.5.0

v0.4.0

What's Changed

Breaking Changes

• Remove torchscript graph builder by @justinchuby in #2444

New Features

• [torch api] Create torch API for PyTorch 2.9 by @justinchuby in #2503

Optimizer and rewriter

• Expose match functionality of rewrite-rule by extracting base classes by @Copilot in #2447
• Implement MatchContext class for rewriter pattern matching by @Copilot in #2455
• [Rewriter] Implement value/node level checkers for pattern matching infrastructure by @Copilot in #2459
• fix: handling of default attrs in SimplifiedLayerNormalization + LayerNormalization🐛 by @KarelZe in #2396
• Add initial support for RotaryEmbedding fusion for onnx opset 23 by @gramalingam in #2450
• Attention mask for GQA fusion by @gramalingam in #2452
• Handle matching against None explicitly by @gramalingam in #2460
• [docs] Document rewriter pattern options by @Copilot in #2406
• Rename fusion files by @gramalingam in #2476
• [Rewriter] Add optimizer to fold Pad operators into Conv by @Johansmm in #2363
• MHA fusion cleanup by @gramalingam in #2481
• Remove double transpose flag in MHA fusion by @gramalingam in #2483
• Add reproduction test case for incorrect slice rewrite and add potential fix by @sebimarkgraf in #2478
• [ort_fusuion] Support fp16 in rms_norm fusion by @titaiwangms in #2491
• Introduce layer-norm fusion by @gramalingam in #2492
• Correctly create empty ints for Constant in rewriter by @justinchuby in #2497
• Add Erf-based Gelu fusion rule by @gramalingam in #2495
• Extend rewriter to handle subgraphs by @gramalingam in #2494
• Minor fix for getting function's graph by @gramalingam in #2504
• Fixes for when attr type can be ambiguous for empty lists by @justinchuby in #2505

Torch Lib

• [torchlib] Improve aten_chunk conversion by @justinchuby in #2469
• Make onnx export SDPA match aten behavior by @IlyasMoutawwakil in #2479
• Add condition to dropout and ref to isnan by @titaiwangms in #2482
• Support aten::scatter.src by @titaiwangms in #2490

Other Changes

• Update VERSION to 0.4.0 by @justinchuby in #2449
• Remove legacy_ir usage in testutil by @justinchuby in #2451
• Remove legacy ir by @justinchuby in #2456
• Remove DORT related tests since it was removed from PyTorch by @justinchuby in #2465
• Update requirements-ort-nightly.txt by @justinchuby in #2471
• Fix logic for converting np array to text by @justinchuby in #2470
• Add a test for boolean attention mask within SDPA by @titaiwangms in #2480
• chore(deps): bump actions/checkout from 4 to 5 by @dependabot[bot] in #2484
• Use onnx-ir 0.1.7 by @justinchuby in #2509
• Minor fixes to onnx to onnxscript converter by @gramalingam in #2510

New Contributors

• @IlyasMoutawwakil made their first contribution in #2479
• @sebimarkgraf made their first contribution in #2478

Full Changelog: v0.3.2...v0.4.0

v0.3.2

What's Changed

Optimizer and rewriter

• Eliminate unnecessary ScatterND by @gramalingam in #2422
• Change loop order during rewrite by @gramalingam in #2427
• Cleanup elimination of redundant scatter-nd: consolidate rules and improve organization by @Copilot in #2426
• [pass][reland] Enable DeduplicateInitializersPass by @titaiwangms in #2429
• [Rewriter]: fuse successive Relu/Clip nodes by @AyoubMDL in #2410
• Add support for onnx fusions by @gramalingam in #2412
• Fix MatchResult.fail() call signature in redundant_scatter_nd.py by @Copilot in #2431
• A couple of minor fixes on rewrite rules by @gramalingam in #2432
• Reorder optimization passes by @gramalingam in #2433
• Cleanup uses of onnxscript.rewriter.pattern - export symbols from main module by @Copilot in #2437
• Improve redundant slice removal by @gramalingam in #2441
• Make TransposeIdentity more robust by @justinchuby in #2443

ONNX IR

• Use onnx_ir common passes by @justinchuby in #2420
• [pass] Enable DeduplicateInitializersPass by @titaiwangms in #2416

Torch Lib

• [torchlib] Fix sdpa dtype in attn_mask by @titaiwangms in #2445

Other Changes

• Update VERSION to 0.3.2 by @justinchuby in #2421
• Copilot instructions by @gramalingam in #2448

Full Changelog: v0.3.1...v0.3.2

v0.3.1

What's Changed

Breaking Changes

• [rewriter] Decouple llama rule sets and make API explicit by @copilot-swe-agent in #2388

Core ONNX Script

• Update autocast.py to fix attribute creation error by @justinchuby in #2365

Optimizer and rewriter

• SDPA fusion cleanup by @gramalingam in #2352
• Enable CSE in optimizer by @titaiwangms in #2361
• Test SDPA fusion via MHA by @gramalingam in #2366
• Always fold the Transpose node in the constant folder by @justinchuby in #2355
• Fix fused matmul check/rewrite functions by @bmehta001 in #2331
• Cast-cast elimination by @gramalingam in #2368
• Re-enable fused matmul rules by @bmehta001 in #2370
• Fusion extensions to improve GQA fusion by @gramalingam in #2374
• fix: pattern match gelu from contrib and onnx ops🐛 by @KarelZe in #2364
• [Rewriter]: Add ∘ MatMul -> Gemm by @AyoubMDL in #2356
• Fixes to MHA fusion by @gramalingam in #2380
• fix: check for rank of bias in bias-gelu fusion🐛 by @KarelZe in #2393
• [torchlib] Implement aten__upsample_bicubic2d_aa and aten__upsample_bilinear2d_aa functions by @copilot-swe-agent in #2383
• Move gemm_to_matmul_add rule to ort fusion rules by @justinchuby in #2398
• Fix fusion ordering for partial rotary embedding by @gramalingam in #2402
• [optimizer] Replace value.nbytes with value.size by @titaiwangms in #2399

Torch Lib

• Add missing converter for _local_scalar_dense by @xadupre in #2367
• [torchlib] Unregister aten::max.other by @titaiwangms in #2377
• Support dynamic shapes for aten_unfold by @xenova in #2407

Documentation

• docs: cleanup documentation for function-based rewrites📄 by @KarelZe in #2359
• Updates to the rewriter tutorial by @gramalingam in #2397
• Add sphinx inter link to onnx_ir by @justinchuby in #2415

Other Changes

• Fix test names for pytest by @justinchuby in #2358
• Require onnx-ir 0.1.1 by @justinchuby in #2360
• [CI] Fix execnet.gateway_base.DumpError: can't serialize <class 'numpy.int64'> by @titaiwangms in #2379
• Move _c_api_utils.py to version_converter package by @copilot-swe-agent in #2401
• Fix proto handling in version converter by @justinchuby in #2411
• Add phi2/phi4 test cases for mha/gqa fusion by @gramalingam in #2409
• Update VERSION to 0.3.1 by @justinchuby in #2414
• Bump onnx ir requirement to 0.1.3 by @justinchuby in #2418
• Create torch_2_8 apis by @justinchuby in #2419

New Contributors

• @KarelZe made their first contribution in #2359
• @copilot-swe-agent made their first contribution in #2383
• @xenova made their first contribution in #2407

Full Changelog: v0.3.0...v0.3.1

v0.3.0

Note

Starting from v0.3, onnxscript.ir is an alias of onnx_ir. Visit https://github.com/onnx/ir-py for source code.

What's Changed

Breaking Changes

• [pass] Update LiftSubgraphInitializersToMainGraphPass to disallow variable shadowing by @justinchuby in #2348
• Formally drop python 3.8 support by @justinchuby in #2354

Optimizer and rewriter

• Fix cross attention in MHA by @gramalingam in #2337
• Implement __repr__ for MatchResult by @justinchuby in #2353

ONNX IR

• Use onnx_ir as a dependency by @justinchuby in #2324

Torch Lib

• [torchlib] Set allowzero=True on Reshape where appropriate by @justinchuby in #2346
• [torchlib] Fix pow.Tensor_Scalar type promotion by @justinchuby in #2335

Other Changes

• Update publish pipelines to use 1ES templates by @justinchuby in #2349

Full Changelog: v0.2.7...v0.3.0

v0.2.7

What's Changed

Optimizer and rewriter

• Optimize causal mask shape by @gramalingam in #2325
• Fix handling of attention-bias in MHA fusion by @gramalingam in #2332
• Ensure rule ordering in MHA fusion by @gramalingam in #2334
• Rewriter: Fold Batchnorm nodes by @AyoubMDL in #2312
• Refine shape optimization by @gramalingam in #2336

ONNX IR

• [IR][fix] Implement copy() for graph inputs/outputs by @justinchuby in #2338
• Add type checks to Attr methods by @justinchuby in #2310
• [IR] Handle external initializers in subgraphs by @justinchuby in #2347

Torch Lib

• [torchlib] Update linear implementation to support 1d weights by @justinchuby in #2340
• [torchlib] Implement floor_divide for int inputs by @justinchuby in #2343

Other Changes

• Update publish pipeline to use an environment by @justinchuby in #2330
• Update publish as a deployment job by @justinchuby in #2333

Full Changelog: v0.2.6...v0.2.7

v0.2.6

What's Changed

Breaking Changes

• Remove the RefAttr class by @justinchuby in #2328
• [IR] Normalize "ai.onnx" domain to "" by @justinchuby in #2283

Optimizer and rewriter

• Add BiasGelu, Erfgelu and SkipLayerNormalization fusions by @shubhambhokare1 in #2222
• Allow sdpa fusion to accept custom scale factor by @shubhambhokare1 in #2210
• Add support for a non-backtracking version of pattern disjunction by @gramalingam in #2242
• Rewrite Skip fusions with check functions by @shubhambhokare1 in #2259
• Add support for backtracking in pattern matcher by @gramalingam in #2273
• Add fusion rules (Whisper optimizations) by @shubhambhokare1 in #2221
• Use OrPatterns to support SkipLayerNormalization rewrite variations by @shubhambhokare1 in #2277
• Unify rule implementations with classes by @justinchuby in #2288

ONNX IR

• [IR] Handle invalid output deserialization by @justinchuby in #2223
• [IR] Improve documentation 1/n by @justinchuby in #2227
• Improve ir.node annotations to accept None inputs by @justinchuby in #2224
• Update type annotations for passes by @justinchuby in #2230
• Add LazyTensor class to implement ir.TensorProtocol by @justinchuby in #2232
• [IR] Support specifying output value in Tape by @justinchuby in #2225
• [IR] Allow to copy an unfrozen version of the Shape by @justinchuby in #2238
• [IR] Use shape.freeze() by @justinchuby in #2247
• [IR] Fix sequence handling in tensor function by @justinchuby in #2252
• [IR] Introduce short name for dtypes by @justinchuby in #2249
• [IR] Display constant tensors for Value by @justinchuby in #2248
• [IR] Refactor TensorBase to simplify implementation by @justinchuby in #2081
• [pass] Update DCE passes by @justinchuby in #2257
• Create short tensor str for nodes by @justinchuby in #2262
• [Pass] Support lifting subgraph initializers to main graph by @titaiwangms in #2266
• Add add/remove initializers passes by @justinchuby in #2253
• [IR] Export all common passes in onnxscript.ir.passes.common by @justinchuby in #2270
• [IR] Record owning graph for input/output/initializers by @justinchuby in #2282
• Add from_onnx_text function to convert ONNX text to IR model by @justinchuby in #2291
• [IR] Docs for Node by @justinchuby in #2297
• [IR] introduce slice support on graph by @Johansmm in #2307

Torch Lib

• [torchlib] Fix scatter reduce on error cases by @justinchuby in #2287

Documentation

• Improvement to IR docs 2/n by @justinchuby in #2229

Other Changes

• Generate opset23 with opgen by @justinchuby in #2226
• Update proto comparison error message by @justinchuby in #2215
• Refactor test models for ort_fusions by @shubhambhokare1 in #2237
• Use ir methods to replace onnx helper by @justinchuby in #2091
• Export version_converter and support model proto by @justinchuby in #2251
• Fix attribute handling in autocast by @justinchuby in #2256
• Update optimize_for_ort call to allow debug and shape_inference modes by @shubhambhokare1 in #2236
• Temporarily skip the whisper test in skip layernorm fusion by @justinchuby in #2286
• Returning choice values in patterns by @gramalingam in #2284
• Fix docs builder pipeline by @justinchuby in #2293
• Split pattern.py by @gramalingam in #2296
• Fix rename within comments by @gramalingam in #2305
• Create publish-dev.yml for ESRP release by @justinchuby in #2101
• Update CONTRIBUTING.md to remove the note about production by @justinchuby in #2308
• Fix RewriterContext import error by @gramalingam in #2314
• Update publish-dev.yml by @justinchuby in #2306
• Fix bug in handling constants in cos sin fusion by @gramalingam in #2319
• Fixes to version converter by @gramalingam in #2318
• Disable fused_matmul_rule_sets by @titaiwangms in #2321
• Remove unnecessary warning by @xadupre in #2327
• Cleanup mha-bias rules using disjunction by @gramalingam in #2326
• Create official ESRP publishing pipelines by @justinchuby in #2320

Full Changelog: v0.2.5...v0.2.6

v0.2.5

What's Changed

Breaking Changes

• Constructor of ir.Function now takes metadata_props from the ir.Graph object. #2182

Core ONNX Script

• Annotate script() with ParamSpec for more accurate typing by @justinchuby in #2178
• Replace ast.NameConstant with ast.Constant and remove duplicates by @justinchuby in #2188

Optimizer and rewriter

• Introduce pattern.any_value by @gramalingam in #2175
• [Pass] Fix bugs in LiftConstantsToInitializersPass by @titaiwangms in #2189
• [pass] Avoid lifting tensors that are too small to initializers by @justinchuby in #2190
• Avoid using fixed value for max_pos_ids in cos_sin_cache fusion by @shubhambhokare1 in #2167
• Add fusion rule to fuse (query, key, value) to a packed QKV for GQA by @shubhambhokare1 in #2174
• Update constant fold to use correct numpy type by @justinchuby in #2204
• Remove legacy optimizer by @justinchuby in #2180
• [Pass] Remove metadata_props and doc_string from the model by @titaiwangms in #2182

ONNX IR

• [Pass] Support lift constants to initializers pass by @titaiwangms in #2160
• [pass] Create topological sort pass by @justinchuby in #2191
• [pass] Create check to ensure in-place passes are actually inplace by @justinchuby in #2192
• [IR] Reconcile graph in Node by @justinchuby in #2183
• [IR] Implement model.graphs() by @justinchuby in #2200
• [passes] Move inliner to common passes by @justinchuby in #2206
• [passes] Remove external_data_folder option from FoldConstantsPass by @justinchuby in #2207
• [pass] Implement checker pass and refactor shape inference by @justinchuby in #2199
• [IR][fix] Save value info for initializers by @justinchuby in #1552
• [IR] Allow pass result as pass input by @justinchuby in #2220
• [pass] Create version converter pass by @justinchuby in #2214
• [pass] Remove unused initialized inputs in DCE by @leshabirukov in #2212

Torch Lib

• [torchlib] Precompute the constant for gelu to avoid precision loss by @justinchuby in #2179
• [torchlib] Fix calls to Unsqueeze to provide correct 1d axes by @justinchuby in #2186
• Implement fft torchop by @bmehta001 in #2141

Documentation

• Update onnxscript documentation page by @justinchuby in #2177

Other Changes

• Remove benchmark from tools by @justinchuby in #2173
• Modify constant-folder to return computed symbolic value map by @gramalingam in #2172
• Update ort-nightly version in test by @justinchuby in #2193
• Updated docs for rewrite-patterns by @LuniaKunal in #2196
• Add test for TopologicalSortPass on functions by @justinchuby in #2198
• Update TorchTensor to use ml_dtypes by @justinchuby in #2201
• Update release.yml to change the section for passes by @justinchuby in #2208
• Fix optimizer tests by @justinchuby in #2217

New Contributors

• @LuniaKunal made their first contribution in #2196
• @bmehta001 made their first contribution in #2141

Full Changelog: v0.2.4...v0.2.5