Sub-token routing in LoRA-adapted transformers adds a finer compression axis for KV caches, with query-independent and query-aware designs that improve efficiency under reduced budgets when combined with token-level selection.
arXiv preprint arXiv:2410.15704 (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sub-Token Routing in LoRA for Adaptation and Query-Aware KV Compression
Sub-token routing in LoRA-adapted transformers adds a finer compression axis for KV caches, with query-independent and query-aware designs that improve efficiency under reduced budgets when combined with token-level selection.