SPA: Towards A Computational Friendly Cloud-Base and On-Devices Collaboration Seq2seq Personalized Generation with Casual Inference
This addresses computational and memory constraints for deploying LLMs on resource-limited devices, though it appears incremental relative to existing on-device seq2seq methods.
The paper tackles the problem of running large language models on low-resource devices by proposing SPA (Side Plugin Adaptation), a lightweight architecture that enables fast on-device inference while maintaining cost efficiency through collaboration between cloud-based LLMs and on-device parameters.
Large language models(LLMs) have shown its outperforming ability on various tasks and question answering. However, LLMs require substantial memory storage on low-resource devices. More critically, the computational speed on these devices is also severely limited. In this paper, we propose SPA(Side Plugin Adaption), a lightweight architecture for fast on-devices inference on the constraints of strict on-devices computation and memory constraints. Compared with other on-devices seq2seq generation, SPA could make a fast and stable inference on low-resource constraints, allowing it to obtain cost effiency. Our method establish an interaction between a pretrained LLMs on-cloud and additive parameters on-devices, which could provide the knowledge on both pretrained LLMs and featured personal feature. Further more, SPA provides a framework to keep feature-base parameters on low computational devices while leave the parameters containing general information on the high computational devices.