OpenAlex ·
DoSA: Dots Sparse Attention
- Published
- Source
- OpenAlex
- Published in
- arXiv (Cornell University)
- DOI
- 10.48550/arxiv.2610.13990
- Original
- Read it at the publisher
- Topics
Abstract
Sparse attention visits few keys, yet finding them can still require scoring every key with every indexer head. We introduce DoSA (Dots Sparse Attention), a lossless method for making this computation conditional while preserving exact token selection. Its central observation is that Top-K selection requires sufficient evidence to reject a candidate, not necessarily its full score. A seed set supplies a lower bound on the winning threshold. Nonnegative head projections and joint residual bounds upper-bound positive contributions, while activation-informed aggregation bounds the magnitude subtracted by negative heads. The certificate directs full scoring toward candidates that remain eligible; exact-score filtering further reduces writeback and selection work. We establish the certificate and its exact-selection conditions, and analyze how geometry and selection margins govern its effectiveness. Our GPU implementation accelerates the complete Indexer by up to 2.74 times over SGLang and 1.69 times over LiteTopK across English, Chinese, and code workloads. End-to-end evaluation on GLM-5.2 and DeepSeek-V3.2 achieves up to 1.94 times and 1.50 times time-to-first-token speedups over the two baselines, respectively.
The authors’ abstract, as arXiv lists it. arXiv’s listings, abstracts included, are free for anyone to reuse.
Read it on ReadSearch
Each opens after you create an account, and brings you back to this paper.
More in Artificial Intelligence
Gaussian Image Steganography via Parameter-Domain Keyed Embeddings
NutriVision: Ingredient-Conditioned Fusion and Prediction for Single-Image Food Nutrition Estimation
AquaBEV-Nav: Learned BEV Occupancy for Underwater Navigation and Exploration
Parameter-Efficient 3D Segmentation of Liver and Liver tumors: Depthwise factorization Scales Better Than Dense Convolution with Spatial Dimensionality
CausalDriveBench: Evaluating Causal Reasoning in Vision-Language-Action Models for Autonomous Driving
Get the few papers worth your time in Artificial Intelligence every morning.
ReadSearch reads the new papers in your field each day and brings you the few worth reading, each with its key finding in a sentence.