Quantization Aware Training and Inference using OpenVINO™ toolkit v1.1

This is an end-to-end workflow, stitched together and deployed through Helm by using microservices/docker images which can be built.

This workflow provides the following capabilities:

1. Quantization Aware Training using Optimum-Intel*[openvino, nncf]
2. Inference using Hugging Face Transformers APIs with Optimum-Intel*
3. Inference using Hugging Face Transformers APIs with Optimum-ONNX Runtime*(OpenVINO™ Execution Provider)
4. Inference using ONNX Runtime APIs with OpenVINO™ Execution Provider
5. Inference using OpenVINO™ Model Server

This is the main release, and it is built using the following components.

1. Intel* Distribution of OpenVINO™ Toolkit v.2022.2
2. Optimum-Intel* and Optimum-ONNX Runtime

This workflow is tested using the bert-large-uncased-whole-word-masking-finetuned-squad model for the Question Answering use case.