From f96aa2b69231820f015785dfb2e6ebe4460172da Mon Sep 17 00:00:00 2001
From: Frank <frank@dankware>
Date: Fri, 14 Aug 2026 12:55:44 -0700
Subject: [PATCH] frank-default-small: refit ctx 800000->700000 for dual-f16 KV
 pool

The f16/f16 KV pool costs 15640 MiB at 800768 cells. At full 800K the
3090 idled at 23966/24576 MiB and the 1472x1472 image warmup graph
failed cudaMalloc (needed +248 MiB). 700416 cells (175104/slot, 4 slots)
leaves ~2.3 GiB free after warmup. Parallel stays 4.
---
 scripts/frank-default-small.env | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/scripts/frank-default-small.env b/scripts/frank-default-small.env
index 13969e4..0f9b968 100644
--- a/scripts/frank-default-small.env
+++ b/scripts/frank-default-small.env
@@ -4,9 +4,11 @@ MODEL_DIR=/home/dank/models
 ALIAS=frank-default-small
 HOST=0.0.0.0
 PORT=7770
-# 4 parallel slots x 200000 ctx each = 800000 total context pool.
-# (Increased from 3×200k to add a 4th parallel stream.)
-CTX_SIZE=800000
+# 4 parallel slots x 175104 ctx each = 700416 total context pool.
+# (2026-08-14: refitted from 800000 when the KV cache went dual-f16; the
+#  f16/f16 pool costs 15640 MiB at 800768 cells and did not fit the 3090's
+#  24 GiB with the image-warmup graph. 700416 cells leaves ~2.3 GiB free.)
+CTX_SIZE=700000
 PARALLEL=4
 # Spec: ngram-mod. n_min=48, n_max=64, n_match=24 (defaults). 4 expert
 # layers back on GPU; 36 on CPU. Batch 8192 / ubatch 3072.