Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
LLM Compression by Block Removal with Constrained Binary Optimization
David Jansen, Roman Rausch, Ali Hashemi +2
In this paper, we formulate the compression of large language models (LLMs) by optimally deleting transformer blocks (``block removal'') as a constrained binary optimization (CBO)…
cs.LG2025
FermiGrad-SVD: An LLM Compression Pipeline with Global Rank Selection and Gauge Fixing
Roman Rausch, David Jansen, Sukhbinder Singh +1
Low-rank factorization of weight matrices is a promising approach to compress large language models (LLMs), but its practical effectiveness depends on allocating ranks across layer…