Artificial Intelligence has achieved significant progress in recent years, with models matching human capabilities in numerous tasks. However, the main hurdle lies not just in creating these models, but in utilizing them optimally in practical scenarios. This is where machine learning inference takes center stage, arising as a key area for research

AI has advanced considerably in recent years, with models surpassing human abilities in diverse tasks. However, the main hurdle lies not just in developing these models, but in deploying them efficiently in real-world applications. This is where inference in AI comes into play, emerging as a primary concern for scientists and industry professionals