ywkang 973a452b77 gqa(adr): sync ADR-0060 KO mirror to current EN (two-kernel design) ...

Regenerate the KO mirror to match the current EN: two SP kernels
(decode=reduce / prefill=ring), TL;DR full code for the 3 decode variants
+ prefill, 'Q replicated / M-fold' and '1 Q head per CUBE' terminology,
contiguous shared KV layout, opt2 tl.wait, and all SB items. Docs only.

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

2026-06-04 23:02:49 -07:00

..

adr

eval: commit milestone bench output (track generated figures + results)

2026-05-22 15:37:27 -07:00

adr-history

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

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

adr-ko

eval: commit milestone bench output (track generated figures + results)

2026-05-22 15:37:27 -07:00

adr-proposed

gqa(adr): sync ADR-0060 KO mirror to current EN (two-kernel design)

2026-06-04 23:02:49 -07:00

diagrams

gemm: test-generated GEMM plots under tests/gemm/ + docs/diagrams/gemm_plots/

2026-05-21 09:58:08 -07:00

onboarding

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

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

report

adr: add INDEX.md (auto-generated by tools/generate_adr_index.py)

2026-05-22 11:15:37 -07:00