Files
LocalAI/backend/cpp
Ettore Di Giacinto 145e45b6f2 docs(paged): exact executable plan for 0003 gather-read
Every edit mapped (gather-index graph input mirroring k_idxs; gather K/V/mask by
one aligned index; n_kv compaction; gated so stock stays byte-identical) with
the token-identical gate and the known risks (mask transpose layout, v_trans).

Assisted-by: Claude:opus-4.8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-06-19 23:12:18 +00:00
..