2025
Lua-LLM: Learning Unstructured-Sparsity Allocation for Large Language Models
Lua-LLM is proposed, a learning-based global pruning framework that explores the optimal unstructured sparsity allocation and achieves flexible allocation for both layer-wise and intra-layer sparsity.
Ming Lu, Jing-Wei Sun, Jun-Qing Lin et al.
· Neural Information Processin... · 1 citation