From f203f1bc403f5d11a9398e7a59606ee85a6d2f5b Mon Sep 17 00:00:00 2001
From: Frank <frank@dankware>
Date: Thu, 13 Aug 2026 22:02:40 -0700
Subject: [PATCH] dankclaw: MTP wins the spec bench; raise ubatch to 4096

MTP (draft-mtp, n_max 3, a4lg MTP-ONLY-Q8_0) benches 15.3-19.5 t/s vs
ngram-mod 6.7-8.7 t/s and passes the strict LCP-reuse parallel test
(sim 0.996 / f_keep 0.994 launch while another slot generates - the
pattern that killed DFlash). ubatch 4096 to use the ~33 GiB VRAM
headroom; watch peak during load.
---
 scripts/frank-default-large.env | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/frank-default-large.env b/scripts/frank-default-large.env
index 4a8c991..07dee93 100644
--- a/scripts/frank-default-large.env
+++ b/scripts/frank-default-large.env
@@ -39,7 +39,7 @@ CACHE_TYPE_V=q8_0
 # ubatch is the compute-graph driver; larger ubatch = more VRAM, faster prefill.
 # Re-verified 2026-08-14 during the spec swap (see benchmark doc).
 BATCH_SIZE=8192
-UBATCH_SIZE=2048
+UBATCH_SIZE=4096
 # Sampling settings — per HauhauCS Qwen3.6-27B model card.
 # Thinking-general: temp=1.0, top_p=0.95, top_k=20, min_p=0.
 # Clients may override per-request; these are the server-side defaults.