LLM Compression by Block Removal with Constrained Binary Optimization 文章

ArXiv CS.CL2026-06-18NEWSen作者: David Jansen, Roman Rausch, Ali Hashemi, David Montero, Rom\'an Or\'us
大语言模型
查看原文 →
关系图谱

LLM Compression by Block Removal with Constrained Binary Optimization · 相关技术

相关技术

MMLU benchmarkconstrained binary optimizationIsing glassblock removalTransformer blockslarge language modelstransformers