kernbench2

Files

T

ywkang 444810c6e3 gqa(adr): TL;DR — Q-replicated/M-fold wording + pointer to S5.6 decode variants

The prior commit updated S0/S10/S5.5 terminology and added S5.6 (3 decode
variants) but left the TL;DR with the old 'all G heads replicated' wording
and no pointer to S5.6. Sync the TL;DR: 'Q replicated (G heads stacked into
the GEMM M-dim, M-fold)', '1 Q head per CUBE', and a one-line pointer to the
3 CPU-pipelining variants in S5.6. Docs only.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-04 22:01:25 -07:00

ADR-0028-par-dtensor-support.md

ADR housekeeping: category prefixes, lifecycle folders, retroactive 0034-0037

2026-05-20 01:15:55 -07:00

ADR-0030-mem-ipcq-physaddr.md

ADR housekeeping: category prefixes, lifecycle folders, retroactive 0034-0037

2026-05-20 01:15:55 -07:00

ADR-0060-algo-gqa-fused-attention-ahbm-ko.md

gqa(adr): ADR-0060 hierarchical CUBE-Group SP — 2-level reduce-to-root

2026-06-04 17:36:18 -07:00

ADR-0060-algo-gqa-fused-attention-ahbm.md

gqa(adr): TL;DR — Q-replicated/M-fold wording + pointer to S5.6 decode variants