CORTEXA
← Browse
arxivcs.LG2026-06-29

Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding

Tianyu Wang, Gourav Rattihalli, Aditya Dhakal, Junbo Li, Zhiwei Ren, Dejan Milojicic, Longfei Shangguan

Dynamic sparse attention (DSA) accelerates long-context LLM decoding by attending to only the top-K KV blocks relevant to each query, but it introduces a serialized selection-to-attention dependency that emerges as a new latency bottleneck. We present PRR, a speculate-reuse-repair runtime that exploits temporal locality in DSA selections to predict likely blocks, speculate the attention over them while selection is in flight, and incrementally repair missed blocks once the true selected set is known. PRR uses a lightweight EMA-based predictor, a profiling-guided speculation budget that keeps speculative work off the critical path, and a FlashAttention-based repair kernel that folds missed blocks into the partial attention state using online-softmax statistics. Across long-context benchmarks and representative DSA methods, PRR reduces per-token decoding latency by up to 40% while preserving downstream task accuracy. Github: https://github.com/Tianyu9748/Incremental_FlashAttention

View free PDFSource page

Related papers

arxivcs.ARcs.AIcs.LG2026-07-24

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding

Chao Fang, Jun Yin, Man Shi, Marian Verhelst

With the rapid adoption of long-context large language models (LLMs), the continuously growing KV cache during decoding has become the critical memory bottleneck. To tackle this challenge, we propose HiKV, a novel algorithm-hardware co-design that exploits KV cache redundancy thr…

View free PDFSource page
arxivcs.LG2026-07-23

Parameter-free Adaptive Sparse Attention via Compression-Based Content Selection

Debarshi Kundu, Swaroop Ghosh, Vasant Honavar

Data-adaptive sparse attention masks substantially outperform fixed patterns (e.g., BigBird and Longformer) and can even exceed dense attention on long sequences. Existing adaptive approaches---including SBM-Transformer, Dynamic Mask Attention, and NSA---typically require additio…

View free PDFSource page
arxivcs.CLcs.LG2026-07-31

PTP: Previous-Token Prediction based LLM Inversion for Near-Exact Prompt Reconstruction

Pirzada Suhail, Nagasai Saketh Naidu, Atanu R Sinha, Amit Sethi

Large language models (LLMs) generate text by auto-regressively sampling the next token. This inherently leads to a many-to-many mapping between prompts and responses, complicating the task of inferring prompts from observed outputs. Prior work on LLM inversion frames prompt reco…

View free PDFSource page
arxivcs.LG2026-07-23

The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and What Actually Works

Yu Wang

Dense per-step supervision is an appealing remedy for sparse-reward, long-horizon LLM agents: reward the agent for predicting its next observation, and memory should follow. We show that under group-normalized RL (GRPO), this recipe does not merely fail -- it destroys the policy.…

View free PDFSource page