2 papers
cs.CL2026
KV Cache Transform Coding for Compact Storage in LLM Inference
Konrad Staniszewski, Adrian ÅaÅcucki
Serving large language models (LLMs) at scale necessitates efficient key-value (KV) cache management. KV caches can be reused across conversation turns via shared-prefix prompts th…
cs.LG2025
Inference-Time Hyper-Scaling with KV Cache Compression
Adrian ÅaÅcucki, Konrad Staniszewski, Piotr Nawrot +1
Inference-time scaling trades efficiency for increased reasoning accuracy by generating longer or more parallel sequences. However, in Transformer LLMs, generation cost is bottlene…