EMC2

Artificial intelligence (AI) continues to proliferate everyday life aided by the advances in automation, algorithms, and innovative hardware and software technologies. With the growing prominence of AI, Multimodal Large Language model (MLLM) has been rising as new foundational model architecture that uses powerful Large Language Model (LLM) with multimodal tasks efficiency. MLLM are able to achieve surprising capabilities based on text and images, suggesting path for Artificial General Intelligence (AGI). With the advent of new frontiers on execution of MLLM, we are facing new challenges on the ecosystem of software/hardware co-design. There is a realization about the energy cost of developing and deploying MLLM. Training and inferencing the most successful MLLM models has become exceedingly power-hungry often dwarfing the energy needs of entire households for years. At the edge, applications which use these LLMs models for inference are ubiquitous in cell phones, appliances, smart..