Advancing SVD-based LLM Compression via Layer-Wise Error Model Search
Low-rank SVD-based compression offers a powerful strategy to reduce the computational costs of LLMs. However, existing methods face two key limitations: (i) global rank allocation, where uncalibrated error proxies fail to capture complex error propagation, and (ii) decomposition quality, where Fisher-based estimators suffer from severe rank collapse. In this work, we address these limitations by…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
