Parameter-efficient fine-tuning (PEFT) is a family of techniques that adapt large pre-trained models to new tasks by updating only a small fraction of parameters, rather than all of them. Methods include LoRA, QLoRA, adapters, prefix tuning, and IA3. PEFT dramatically reduces the memory and compute needed for fine-tuning, making it possible for a startup to customize a billion-parameter model on a single GPU. It is now the default approach for adapting LLMs in production.