Batched Low-Rank Adaptation of Foundation Models

arXiv:2312.05677v2 Announce Type: replace
Abstract: Low-Rank Adaptation (LoRA) has recently gained attention for fine-tuning foundation models by incorporating trainable low-rank matrices, thereby reducing the number of trainable parameters. While LoRA offers numerous advantages, its applicability for real-time serving to a diverse and global user base is constrained by its incapability to handle multiple task-specific adapters efficiently. This imposes a performance bottleneck in scenarios requiring personalized, task-specific adaptations for each incoming request. To mitigate this constraint, we introduce Fast LoRA (FLoRA), …

abstract advantages arxiv attention cs.ai cs.cl cs.lg diverse fine-tuning foundation global lora low low-rank adaptation multiple parameters real-time type