From 056433555fd6d871af2abb8807210bc44a1e3ba9 Mon Sep 17 00:00:00 2001
From: Vuong Hoang <vh@phasefinal.com>
Date: Mon, 28 Sep 2026 14:33:39 -0700
Subject: [PATCH] memory: Bonsai MMVQ-threshold follow-up (N=8 1.06x -> 1.21x);
 build image removed

---
 persistent-memory.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/persistent-memory.md b/persistent-memory.md
index 8a1c5e7..f6ea7a2 100644
--- a/persistent-memory.md
+++ b/persistent-memory.md
@@ -278,7 +278,7 @@ _As of 2026-09-27 ~0900 PT._
 
 ## Recent decisions
 
-- `[2026-09-28]` **Bonsai ternary spike on fv-ml1 GPU 3 (Prime via brokkr): at the 275 W cap, PQ2_0 is 1.93x Q4_K_XL at N=1 but only 1.06x at N=8 (PTQ1_0 1.24x), recovering to ~1.37x at N=16. That is likely the fork's MMVQ-to-MMQ batch threshold (read at source, untested).** Positive control passed on tg128 (+1.1%). nvidia-smi's sw_power_cap flag never fires on this card, so "at cap" is judged from board draw. Runs are in `fv-ml1:/tank/spikes/bonsai-2026-09-28/runs/` and on the Booth; the 9.8 GB build image stays until brokkr says whether to do the threshold test.
+- `[2026-09-28]` **Bonsai ternary spike on fv-ml1 GPU 3 (Prime via brokkr): at the 275 W cap, PQ2_0 is 1.93x Q4_K_XL at N=1 but only 1.06x at N=8 (PTQ1_0 1.24x), recovering to ~1.37x at N=16.** Positive control passed on tg128 (+1.1%). nvidia-smi's sw_power_cap flag never fires on this card, so "at cap" is judged from board draw. Follow-up (brokkr): moving PQ2_0 onto MMQ from batch 6, like Q4_K (mmvq.cu, `ne11 <= 5`), lifts N=8 to 1.21x, so the dip was partly a kernel threshold. The residual gap is not power. Runs are in `fv-ml1:/tank/spikes/bonsai-2026-09-28/runs{,-mmvq5}/` and on the Booth. The build image was removed; `Dockerfile.build` recreates it.
 - `[2026-09-28]` **blender-run gained `--cpu` (no GPU attached) and a fixed hostname `fv-ml1-blender` (draupnir).** The design stage never renders, so it stays off GPU 3.
 - `[2026-09-28]` **Blender extensions live in a read-only System repo built from a sha256 lock, enabled by a hook, opt-in for blender-run (`--extensions`).** SurfacePsycho's eval() is patched to literal_eval (a proven safe-mode escape). → `stacks/blender/README.md` § Extensions
 - `[2026-09-27]` **hermes-gateway restarted 0401 for highseat-dev** (SVOS v2.1.12: `propose_decision` gained `seat_up`, and Hermes reads the plugin only at start). The plugin load was verified at file level; the end-to-end proof is Miranda's first seat_up card. Enabling `zellij-fleet@Claude` at boot remains Prime's call.