v0.2.0

What's Changed

• [torchlib] Simplify squeeze by @justinchuby in #2047
• [torchlib] Add memory_format to ones_like by @justinchuby in #2049
• Fix aten_pow when first input is a python constant by @xadupre in #2048
• [torchlib] Fix various implementations by @justinchuby in #2050
• Expose opset22 by @justinchuby in #2053
• Refactor ort specific fusions by @gramalingam in #2039
• [torchlib] Fix reflection pad by @justinchuby in #2037
• [torchlib] Make matmul trace_only by @justinchuby in #2055
• Minor cleanup by @gramalingam in #2056
• [torchlib] Simplify aten_trunc implementation by @justinchuby in #2057

Full Changelog: v0.1.0...v0.1.1