QubitCache: Quantum-Inspired Probabilistic Attention Preservation for KV-Cache Compression

Large language model inference faces a critical memory bottleneck from KV cache, which grows linearly with sequence length and dominates GPU memory during long-context generation. Existing compression methods reduce memory through token eviction but irreversibly discard attention relationships essen...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Jieui Kang, Jaeyoung Choi, Wonhui Noh, Jaehyeong Sim
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	IEEE 2026-01-01
Цуврал:	IEEE Access
Нөхцлүүд:	Large language models quantum-inspired computing KV cache attention mechanism efficient machine learning deep learning
Онлайн хандалт:	https://ieeexplore.ieee.org/document/11479587/
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!