AI RESEARCH

LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models

arXiv CS.LG

ArXi:2605.17289v1 Announce Type: new Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shifting the bottleneck from inference execution to the pruning algorithm. State-of-the-art methods for unstructured LLM pruning are layer-wise surrogates derived from the Optimal Brain Surgeon principle, and they sacrifice end-to-end accuracy, especially under aggressive sparsity.