{"type": "article", "title": "Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/faster-than-flash-exploiting-attention-sparsity-for-efficient-long-context", "original_source": "https://arxiv.org/abs/2609.00097", "published": "2026-09-02T04:00:00+00:00", "accessed": "2026-09-02", "id": "faster-than-flash-exploiting-attention-sparsity-for-efficient-long-context"}