attend op• Data kinds: tokens × tokens × tokens → tokens
• Call: import fullseye as fs; fs.ledger.attention_tiled(query, key, value, tile: 'int' = 64, mask=None, window=None, scale=None) -> 'np.ndarray' (to call the implementation directly, import llmcore; llmcore.attention_tiled(query, key, value, tile: 'int' = 64, mask=None, window=None, scale=None) -> 'np.ndarray'; from the registry, opsllmcore.get("attention_tiled"))
> This operator's description has not been translated yet. The original text follows as it is.
タイル + online softmax の注意(FlashAttention の芯)→ tokens。近似ではない。
Dao ら 2022。key/value を `tile` 行ずつ読み、走っている最大値と分母をその場で
補正しながら足す。作る中間行列は (T, `tile`) だけで、(T, T) を一度も作らない ——
速さの出どころは近似ではなく、置き場所。`attention_softmax` との相対差は
タイル 128 枚でも 1.2e-15(タイル 1 枚で 8.2e-16 なので、枚数を 128 倍しても 1.5 倍)。
Args:
query: (T, d) float。
key: (S, d) float。
value: (S, dv) float。
tile: 一度に読む key/value の行数。小さいほど中間行列が小さく、枚数が増える。
mask: None / `"causal" / "window"` / (T, S) の bool 配列。
window: `mask="window"` のときの窓幅。
scale: スコアの倍率。None なら 1/√d。
Returns:
tokens (T, dv) float: `attention_softmax` と機械精度で一致する。
• Sample-data catalog (download URLs / licences) — 2-D uses skimage.data (BSD/public domain) plus synthetic images; 3-D lists download URLs for real data sources (Stanford, PDS, …).
• Operator provenance and references — the sources of the research/methods this op family came from.
• The canonical algorithm (author, year) and its uses are named in the family usage guide above.
• poc_attention_identities — py -3.11 examples/poc_attention_identities.py
tokens as input)rms_norm · rope_rotate · attention_scores · attention_apply · attention_softmax · attention_linear · attention_grouped · kv_cache_decode
attend)attention_softmax · attention_linear · attention_grouped
*Provenance: llmcore.py — LLMCORE operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*
© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.