GradPruner: Gradient-Guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915757786398720 |
|---|---|
| author | Huang, Wei Cheng, Anda Wang, Yinggui |
| author_facet | Huang, Wei Cheng, Anda Wang, Yinggui |
| contents | Fine-tuning Large Language Models (LLMs) with downstream data is often considered time-consuming and expensive. Structured pruning methods are primarily employed to improve the inference efficiency of pre-trained models. Meanwhile, they often require additional time and memory for training, knowledge distillation, structure search, and other strategies, making efficient model fine-tuning challenging to achieve. To simultaneously enhance the training and inference efficiency of downstream task fine-tuning, we introduce GradPruner, which can prune layers of LLMs guided by gradients in the early stages of fine-tuning. GradPruner uses the cumulative gradients of each parameter during the initial phase of fine-tuning to compute the Initial Gradient Information Accumulation Matrix (IGIA-Matrix) to assess the importance of layers and perform pruning. We sparsify the pruned layers based on the IGIA-Matrix and merge them with the remaining layers. Only elements with the same sign are merged to reduce interference from sign variations. We conducted extensive experiments on two LLMs across eight downstream datasets. Including medical, financial, and general benchmark tasks. The results demonstrate that GradPruner has achieved a parameter reduction of 40% with only a 0.99% decrease in accuracy. Our code is publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_19503 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GradPruner: Gradient-Guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs Huang, Wei Cheng, Anda Wang, Yinggui Computation and Language Artificial Intelligence Fine-tuning Large Language Models (LLMs) with downstream data is often considered time-consuming and expensive. Structured pruning methods are primarily employed to improve the inference efficiency of pre-trained models. Meanwhile, they often require additional time and memory for training, knowledge distillation, structure search, and other strategies, making efficient model fine-tuning challenging to achieve. To simultaneously enhance the training and inference efficiency of downstream task fine-tuning, we introduce GradPruner, which can prune layers of LLMs guided by gradients in the early stages of fine-tuning. GradPruner uses the cumulative gradients of each parameter during the initial phase of fine-tuning to compute the Initial Gradient Information Accumulation Matrix (IGIA-Matrix) to assess the importance of layers and perform pruning. We sparsify the pruned layers based on the IGIA-Matrix and merge them with the remaining layers. Only elements with the same sign are merged to reduce interference from sign variations. We conducted extensive experiments on two LLMs across eight downstream datasets. Including medical, financial, and general benchmark tasks. The results demonstrate that GradPruner has achieved a parameter reduction of 40% with only a 0.99% decrease in accuracy. Our code is publicly available. |
| title | GradPruner: Gradient-Guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.19503 |