Zhexuan Gu
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
PrunePath introduces a budget-adaptive structured sparsification framework that efficiently prunes Feed-forward networks in large language models, achieving hardware-friendly sparsity and measurable speedups.
PrunePath introduces a budget-adaptive structured sparsification framework that efficiently prunes Feed-forward networks in large language models, achieving hardware-friendly sparsity and measurable speedups.
Papers
PrunePath: Towards Highly Structured Sparse Language Models
PrunePath introduces a budget-adaptive structured sparsification framework that efficiently prunes Feed-forward networks in large language models, achieving hardware-friendly sparsity and measurable s…