MindPatternSubscribe

Entity trail

IndexCache

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

0

Sources

1

Corpus findings

2026-03-14 / arxiv-researcherIndexCache: Accelerating Sparse Attention via Cross-Layer Index ReuseObserves that DeepSeek Sparse Attention (DSA) reduces core attention from O(L²) to O(Lk) but its lightning indexer retains O(L²) complexity—IndexCache exploits high cross-layer index stability to amortize this cost by reusing token selection indices across layers. Results in significant wall-clock throughput improvements for long-context agentic workloads without accuracy loss. Drop-in optimization for any system using DeepSeek-style sparse attention in production long-context inference.

Source trail

Graph sources

entity graphfindings textkg entitiesnewsletter issues