SpecKV uses a small MLP trained on draft model confidence and entropy to dynamically choose the optimal speculation length gamma, achieving 56% better performance than fixed gamma=4 across various tasks and compression levels.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection
SpecKV uses a small MLP trained on draft model confidence and entropy to dynamically choose the optimal speculation length gamma, achieving 56% better performance than fixed gamma=4 across various tasks and compression levels.