v1.16.0: OpenVINO config, SD hybrid quantization

Add hybrid quantization for Stable Diffusion pipelines by @l-bat in #584

from optimum.intel import OVStableDiffusionPipeline, OVWeightQuantizationConfig

model_id = "echarlaix/stable-diffusion-v1-5-openvino"
quantization_config = OVWeightQuantizationConfig(bits=8, dataset="conceptual_captions")
model = OVStableDiffusionPipeline.from_pretrained(model_id, quantization_config=quantization_config)

Add openvino export configs by @eaidova in #568

Enabling OpenVINO export for the following architectures enabled : Mixtral, ChatGLM, Baichuan, MiniCPM, Qwen, Qwen2, StableLM

Add support for export and inference for StarCoder2 models by @eaidova in #619