3 papers
cs.AI2026
LinearKV: One Cached State Suffices for Position-Independent Caching in Hybrid LLMs
Yirui Liu, Ruoling Qi, Longwen Wang +5
LLM serving is increasingly accelerated by position-independent caching (PIC). Existing PIC methods, however, are built for full-attention models, where a token-indexed KV cache un…
cs.CL2026
Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression
Ruoling Qi, Yirui Liu, Xuaner Wu +6
The deployment of Large Language Models is constrained by the memory and bandwidth demands of static weights and dynamic Key-Value cache. SVD-based compression provides a hardware-…
cs.CL2026
KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs
Jian Chen, Zhuoran Wang, Jiayu Qin +6
Large language models rely on kv-caches to avoid redundant computation during autoregressive decoding, but as context length grows, reading and writing the cache can quickly satura…