LLMs as On-demand Customizable Service
This addresses scalability and resource issues for users of LLMs, but it appears incremental as it builds on existing distributed computing concepts.
The paper tackles the challenges of training, deploying, and accessing Large Language Models (LLMs) by proposing a hierarchical, distributed architecture to enhance accessibility and deployability across heterogeneous platforms like laptops and IoT devices, enabling on-demand customizable service with optimal resource trade-offs.
Large Language Models (LLMs) have demonstrated remarkable language understanding and generation capabilities. However, training, deploying, and accessing these models pose notable challenges, including resource-intensive demands, extended training durations, and scalability issues. To address these issues, we introduce a concept of hierarchical, distributed LLM architecture that aims at enhancing the accessibility and deployability of LLMs across heterogeneous computing platforms, including general-purpose computers (e.g., laptops) and IoT-style devices (e.g., embedded systems). By introducing a "layered" approach, the proposed architecture enables on-demand accessibility to LLMs as a customizable service. This approach also ensures optimal trade-offs between the available computational resources and the user's application needs. We envision that the concept of hierarchical LLM will empower extensive, crowd-sourced user bases to harness the capabilities of LLMs, thereby fostering advancements in AI technology in general.