Skip to content

v0.4.0

Choose a tag to compare

@justinchuby justinchuby released this 22 Aug 20:44
f5b58e0

What's Changed

Breaking Changes

New Features

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

Other Changes

New Contributors

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