From d8da7a9eb79d2dd6c62b4134fc0a4e90187d6db2 Mon Sep 17 00:00:00 2001
From: Frank <frank@dankware>
Date: Tue, 6 Oct 2026 18:30:35 -0700
Subject: [PATCH] frank-secondary: ubatch 2048 (the second rung inside the 112k
 headroom)

Frank's order the same night. The 1024->2048 rung measured +4.6 %
prefill for 616 MiB on the 3090 (2026-10-05 boot pair); the 112k cut
left 1,751 MiB free, so it rides with ~1.1 GiB predicted margin.
Decode is ubatch-invariant; batch 4096 >= 2048 keeps the seam happy.
---
 scripts/frank-secondary.env     | 10 ++++++----
 tests/frank_secondary_unit.bats |  6 +++---
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/scripts/frank-secondary.env b/scripts/frank-secondary.env
index b26b438..f755a32 100644
--- a/scripts/frank-secondary.env
+++ b/scripts/frank-secondary.env
@@ -68,11 +68,13 @@ PARALLEL=2
 
 # Compute-buffer geometry. Ubatch is a prefill knob (decode never moves);
 # the 1024 rung was the first A/B back once the per-slot context dropped
-# to 112k (2026-10-06 evening) and freed ~1 GiB of KV. The pair is a
-# measurement, not a law (loud failure at graph capture if it does not
-# fit).
+# to 112k (2026-10-06 evening), and 2048 is the second (Frank, same night)
+# — the rung measured +4.6 % prefill for 616 MiB on the 3090 (2026-10-05
+# boot pair), affordable inside the 1,751 MiB the 112k cut freed. The pair
+# is a measurement, not a law (loud failure at graph capture if it does
+# not fit).
 BATCH_SIZE=4096
-UBATCH_SIZE=1024
+UBATCH_SIZE=2048
 
 # The KV contract for this swap (Frank, 2026-10-05): q8_0 K + q8_0 V —
 # llama.cpp's FP8 class. The flags stay explicit so the choice is visible in
diff --git a/tests/frank_secondary_unit.bats b/tests/frank_secondary_unit.bats
index 26f242c..4cbe403 100755
--- a/tests/frank_secondary_unit.bats
+++ b/tests/frank_secondary_unit.bats
@@ -146,10 +146,10 @@ argv_value() {
     # RCO-IQ3_XXS weights 10,148 MiB (10,442,827,392 B) — 1.56 GiB LIGHTER
     # than the IQ3_S-mtp predecessor — + vision tower ~1.4 GiB (931,145,888
     # B BF16 mmproj at the measured ~1.45x cost law) + compute buffers at
-    # ubatch 1024 + CUDA graphs + TWO DeltaNet states (~150 MiB each) + the
+    # ubatch 2048 + CUDA graphs + TWO DeltaNet states (~150 MiB each) + the
     # MTP draft ctx => 14 GiB budgeted. Two 114,688 slots are the
-    # 2026-10-06 evening shape (the lighter per-slot funds the ubatch
-    # increase); a THIRD slot must not fit. Arithmetic, not a boot log:
+    # 2026-10-06 late shape (the lighter per-slot funds the ubatch
+    # rungs); a THIRD slot must not fit.
     # change CTX_SIZE and this bites before the deploy does; the boot's
     # nvidia-smi free is the measured truth.
     ctx="$(sed -nE 's/^CTX_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"