greedy-algorithms

This paper revisits Kashin-decomposition-based weight quantization for large language models and proposes an improved algorithm using structured orthogonal transforms, reducing computational cost and ensuring numerical stability compared to methods like OPTQ and QuIP.

Proposes a framework for selecting complementary LLMs as proposers in ensemble systems, reformulating proposer selection as a combinatorial problem and exploring greedy algorithms for efficient performance-cost trade-offs.