#artificial intelligence
Dec 2025
OPTIMA: Optimal One-shot Pruning for LLMs via Quadratic Programming Reconstruction
An accelerator-friendly QP solver is implemented that accumulates one Hessian per weight matrix and solves many small QPs in parallel with a convergence certificate per column, enabling one-shot post-training pruning at scale on a single accelerator without fine-tuning.
Mohammad Mozaffari, Samuel Kushnir, Maryam Mehri Dehnavi et al.
· arXiv.org · 2 citations