Jae W. Lee

4 papers Seoul National University

• DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision Assignment
• KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
• KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
• NestedFP: High-Performance, Memory-Efficient Dual-Precision Floating Point Support for LLMs