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