KV offloading hurts accuracy on context-heavy tasks because of low-rank key projections and bad landmarks, but a simpler strategy improves results across models and benchmarks.
Title resolution pending
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
-
KV Cache Offloading for Context-Intensive Tasks
KV offloading hurts accuracy on context-heavy tasks because of low-rank key projections and bad landmarks, but a simpler strategy improves results across models and benchmarks.