5 papers
Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training
Chengqian Zhang, Wei Zhu, Kyumin Lee
Post-training has become essential for adapting large language models (LLMs) to complex downstream behaviors, including instruction following, preference alignment, and multi-step…
ShapLoRA: Allocation of Low-rank Adaption on Large Language Models via Shapley Value Inspired Importance Estimation
Yi Zhao, Qinghua Yao, Xinyuan song +1
Low-rank adaption (LoRA) is a representative method in the field of parameter-efficient fine-tuning (PEFT), and is key to Democratizating the modern large language models (LLMs). T…
ML-Triton, A Multi-Level Compilation and Language Extension to Triton GPU Programming
Dewei Wang, Wei Zhu, Liyang Ling +5
In the era of LLMs, dense operations such as GEMM and MHA are critical components. These operations are well-suited for parallel execution using a tilebased approach. While traditi…
PARA: Parameter-Efficient Fine-tuning with Prompt Aware Representation Adjustment
Zequan Liu, Yi Zhao, Ming Tan +2
In the realm of parameter-efficient fine-tuning (PEFT) methods, while options like LoRA are available, there is a persistent demand in the industry for a PEFT approach that excels…
MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning
Jingfan Zhang, Yi Zhao, Dan Chen +3
Low-rank adaptation (LoRA) and its mixture-of-experts (MOE) variants are highly effective parameter-efficient fine-tuning (PEFT) methods. However, they introduce significant latenc…