PRR accelerates dynamic sparse attention decoding in long-context LLMs via EMA-based prediction, speculative attention, and FlashAttention repair, achieving up to 40% latency reduction.
arXiv preprint arXiv:2603.13430 , year=
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
-
Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding
PRR accelerates dynamic sparse attention decoding in long-context LLMs via EMA-based prediction, speculative attention, and FlashAttention repair, achieving up to 40% latency reduction.