{"type": "article", "title": "IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/indexcache-accelerating-sparse-attention-via-cross-layer-index-reuse", "original_source": "https://github.com/THUDM/IndexCache", "published": "2026-06-17T12:00:31+00:00", "accessed": "2026-06-17", "id": "indexcache-accelerating-sparse-attention-via-cross-layer-index-reuse"}