Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression
Paper • 2604.01609 • Published • 11
None defined yet.
Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression
KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs