AI RESEARCH
BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding
arXiv CS.CL
•
ArXi:2512.12087v2 Announce Type: replace The growing demand for long-context inference capabilities in Large Language Models (LLMs) has intensified the computational and memory bottlenecks inherent to the self-attention mechanism. To address this challenge, we