A survey organizing serving-time KV cache optimization techniques into temporal, spatial, and structural system behaviors, analyzing cross-behavior co-design patterns and open challenges.
BALI (Jurkschat et al., 2025) measures LLM inference across six frameworks or acceler- ation approaches
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization
A survey organizing serving-time KV cache optimization techniques into temporal, spatial, and structural system behaviors, analyzing cross-behavior co-design patterns and open challenges.