{"ok":true,"entity":{"id":"flash-attention","name":"FlashAttention","entityType":"product","officialName":"FlashAttention","canonicalName":"FlashAttention","displayName":"FlashAttention","category":"高速Attentionカーネル","shortDescription":"Tri Daoらが開発した、メモリ効率と速度を大幅に改善したAttention計算の実装。多くのLLM学習・推論基盤で標準的に採用されている。","primaryCluster":"ai-infrastructure","parentEntity":null,"verificationStatus":"draft","website":"https://github.com/Dao-AILab/flash-attention","updatedAt":"2026-07-20T08:41:20.341Z","secondaryClusters":[],"alias":["Flash Attention"],"searchKeywords":["attention kernel","IO-aware","memory efficient"]},"referenceIndex":["P-01-001","P-02-001","P-04-001","P-02-002","P-01-002","P-05-001"]}