Any plans on supporting ollama with OpenVINO acceleration?

[apram0d]

Currently, ollama 7b/70b models are running comparatively slow on Intel systems(CPU). Also, it has support for AMD GPUs and Nvidia but not Intel. The 70b/7b llama hf model that I used from https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/254-llm-chatbot/254-llm-chatbot.ipynb is faster than from ollama. I feel OpenVINO acceleration gives better boost here. I am sorry but I am unable to get the latest update on support of these models on openvino model_server.