Optimum-intel

* Fix OpenVINO Seq2Seq model export for optimum v1.7.3 by echarlaix in https://github.com/huggingface/optimum-intel/pull/253

* Fix IPEX quantization model output by sywangyi in https://github.com/huggingface/optimum-intel/pull/218
* Fix INC pruning and QAT combination by xin3he in https://github.com/huggingface/optimum-intel/pull/241
* Fix loading of stable diffusion model when model config is not adapted by echarlaix in https://github.com/huggingface/optimum-intel/pull/237
* Enable VAE encoder openvino export by echarlaix in https://github.com/huggingface/optimum-intel/pull/224
* Fix openvino fp16 conversion for seq2seq models by echarlaix in https://github.com/huggingface/optimum-intel/pull/238
* Disable scheduler, tokenizer, feature extractor loading when provided by echarlaix in https://github.com/huggingface/optimum-intel/pull/245
* Fix OVTrainer openvino export for structurally pruned model by yujiepan-work in https://github.com/huggingface/optimum-intel/pull/236

NNCF Joint pruning quantization and distillation

Enable joint pruning, quantization and distillation through the `OVTrainer` by vuiseng9 in https://github.com/huggingface/optimum-intel/pull/150


Stable Diffusion models OpenVINO export and inference

Add stable diffusion OpenVINO pipeline by echarlaix in https://github.com/huggingface/optimum-intel/pull/195

python
from optimum.intel.openvino import OVStableDiffusionPipeline

model_id = "stabilityai/stable-diffusion-2-1"
stable_diffusion = OVStableDiffusionPipeline.from_pretrained(model_id, export=True)
prompt = "sailing ship in storm by Rembrandt"
images = stable_diffusion(prompt).images

* Standardize OpenVINO inference and quantization with INC and ORT by echarlaix in https://github.com/huggingface/optimum-intel/pull/185
* Fix past key values usage following transformers `4.26.0` release by fxmarty in https://github.com/huggingface/optimum-intel/pull/187

* Fix OpenVINO export for NNCF quantized model by echarlaix in https://github.com/huggingface/optimum-intel/pull/176
* Fix ONNX export INC trainer by echarlaix in https://github.com/huggingface/optimum-intel/pull/177
* Fix OpenVINO Seq2Seq models inference by echarlaix in https://github.com/huggingface/optimum-intel/pull/175
* Enable JIT mode for IPEX to improve inference performance for pipelines by sywangyi in https://github.com/huggingface/optimum-intel/pull/163
* Enable OpenVINO Runtime support for audio classification by echarlaix in https://github.com/huggingface/optimum-intel/pull/166
* Fix INC model loading by echarlaix in https://github.com/huggingface/optimum-intel/pull/170
* Fix INCTrainer distillation and evaluation steps by echarlaix in https://github.com/huggingface/optimum-intel/pull/182

* Fix INC ONNX export (https://github.com/huggingface/optimum-intel/pull/154)
* Add IPEX backend support to INC quantization (https://github.com/huggingface/optimum-intel/pull/161)
* Add Neural Coder support (https://github.com/huggingface/optimum-intel/pull/146)
* Make the batch size and sequence length axis dynamic for causal language model for OpenVINO Runtime (https://github.com/huggingface/optimum-intel/pull/168)