v1.11.0: Extended ONNX, ONNX Runtime, BetterTransformer support

Extended ONNX and ONNX Runtime support

Add ONNX export and ONNX Runtime inference support for gpt bigcode.

• Add ONNX / ONNXRuntime support for StarCoder by @JingyaHuang in #1042

Extended BetterTransformer support

BetterTransformer now supports Llama 2 and bark.

Training and autocast are now supported for most architectures, please refer to the documentation for more details: https://huggingface.co/docs/optimum/main/en/bettertransformer/overview

• Support Llama 2 in BetterTransformer. by @noamwies in #1235
• BetterTransformer support training & autocast for all archs by @fxmarty in #1225
• Add bark into bettertransformer by @ylacombe in #1199
• Drop mask for training in all cases for BetterTransformer & precise documentation by @fxmarty in #1250

Major bugfixes

• Update ORT training to be compatible with transformers 4.31 by @JingyaHuang in #1227

Other improvements and bugfix

• add upgrade strategy by @echarlaix in #1228
• fix typo README by @echarlaix in #1230
• Fix OwlViT exporter config by @regisss in #1188
• Add example SD XL documentation by @echarlaix in #1233
• fix SD loading when safetensors weights only by @echarlaix in #1232
• fix optimum-intel min version by @echarlaix in #1234
• fix typo documentation by @echarlaix in #1238
• update documentation by @echarlaix in #1240
• Update onnxruntime minimum version to 1.11 by @fxmarty in #1244
• ORT quantizes by default all ops by @fxmarty in #1246

New Contributors

• @ylacombe made their first contribution in #1199
• @noamwies made their first contribution in #1235

Full Changelog: v1.10.0...v1.11.0