From a08be1641f213dce558890abb9a84ffc13cd79f8 Mon Sep 17 00:00:00 2001
From: Frank <frank@dankware>
Date: Tue, 18 Aug 2026 08:01:17 -0700
Subject: [PATCH] frank-default-large: full native 262144 context per slot
 (524288 total)

llama.cpp splits -c across -np slots; to give each of the 2 slots the full
262144 native context, set CTX_SIZE=524288. KV ~32 GiB; fits the 96 GiB
unified pool. Update env default, serve-script fallback, and the deployment
doc line.
---
 docs/deployment.md              |  5 +++--
 scripts/frank-default-large.env | 14 ++++++++------
 scripts/serve-frank-large.sh    |  2 +-
 3 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/docs/deployment.md b/docs/deployment.md
index c9ce99a..11986d8 100644
--- a/docs/deployment.md
+++ b/docs/deployment.md
@@ -120,8 +120,9 @@ The active service on Dankclaw is the CIRU ROCmFPX llama.cpp runtime serving
 companions) under the alias `frank-default-large` on port 52625. It runs
 `/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server` (ROCm
 7.15 SDK in the retired ling3-ciru venv) with native depth-4 MTP
-(`--spec-type draft-mtp`), f16 KV for both K and V, context 262144 across
-2 parallel slots, batch 2048 / ubatch 2048, 32 context checkpoints, 8 GiB
+(`--spec-type draft-mtp`), f16 KV for both K and V, full 262144 context per
+slot (524288 total across 2 parallel slots), batch 2048 / ubatch 2048, 32
+context checkpoints, 8 GiB
 prompt cache, and reasoning in deepseek format. The unit file is
 `scripts/frank-default-large.service`. It launches through
 `scripts/serve-frank-large.sh`, which reads tunables from
diff --git a/scripts/frank-default-large.env b/scripts/frank-default-large.env
index 95c6415..3a4a8cc 100644
--- a/scripts/frank-default-large.env
+++ b/scripts/frank-default-large.env
@@ -39,12 +39,14 @@ ALIAS=frank-default-large
 BIND_ADDR=0.0.0.0
 LISTEN_PORT=52625
 
-# Serving: 256K context (native max, n_ctx_train = 262144), 2 slots, f16 KV,
-# context checkpoints, prompt cache. Native MTP depth-4. The Strix Halo is
-# unified memory; the addressable pool is 96 GiB (VRAM is a pointer). KV at
-# 262144 x 2 slots is ~32 GiB (64 KiB/cell, 16 full-attn layers); total
-# sits well inside the 96 GiB pool.
-CTX_SIZE=262144
+# Serving: full native 256K context PER SLOT (n_ctx_train = 262144), 2
+# slots. -c is the TOTAL context; llama.cpp splits it across the -np slots,
+# so to give each slot the full 262144 we set CTX_SIZE = 2 x 262144 =
+# 524288. f16 KV, context checkpoints, prompt cache, native MTP depth-4.
+# The Strix Halo is unified memory; the addressable pool is 96 GiB (VRAM is
+# a pointer). KV at 524288 x 64 KiB/cell is ~32 GiB; total sits inside the
+# 96 GiB pool.
+CTX_SIZE=524288
 PARALLEL=2
 BATCH_SIZE=2048
 UBATCH_SIZE=2048
diff --git a/scripts/serve-frank-large.sh b/scripts/serve-frank-large.sh
index 25b5eee..d7d42a4 100755
--- a/scripts/serve-frank-large.sh
+++ b/scripts/serve-frank-large.sh
@@ -37,7 +37,7 @@ fi
 : "${ALIAS:=frank-default-large}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=52625}"
-: "${CTX_SIZE:=262144}"
+: "${CTX_SIZE:=524288}"
 : "${PARALLEL:=2}"
 : "${BATCH_SIZE:=2048}"
 : "${UBATCH_SIZE:=2048}"