From dcdf044aa110b2ef73bf5834687fca254f785fe1 Mon Sep 17 00:00:00 2001
From: Frank <frank@dankware>
Date: Sat, 26 Sep 2026 17:11:31 -0700
Subject: [PATCH] frank-primary: exact prefill, the only mode the streamed tier
 runs

--ds4-prefill dense made requires_monolithic_model() true, and a monolithic
load asks ggml for the entire 187 GiB expert set as one device-0 buffer:
"allocating 191932.25 MiB on device 0: cudaMalloc failed: out of memory",
followed by "monolithic HIP load required for dense prefill". Approximate
prefill (dense, sparse) is expressible only where the experts are resident
(in-process owners). exact feeds the prompt token by token, which is the
path the hybrid tier streams experts for. Chunk follows DS41.md's
cold-expert recipe (1024).
---
 .../frank-primary/frank-primary-entrypoint.sh | 25 ++++++++++++-------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/dankserver/frank-primary/frank-primary-entrypoint.sh b/dankserver/frank-primary/frank-primary-entrypoint.sh
index 22cfdd6..2ad4b49 100755
--- a/dankserver/frank-primary/frank-primary-entrypoint.sh
+++ b/dankserver/frank-primary/frank-primary-entrypoint.sh
@@ -15,13 +15,20 @@
 # that branch — see serverAppConfigs-docs/LLM/frank-primary-lucebox-ds41.md.
 #
 # LAUNCH SHAPE (server/docs/DS41.md — the V4.1 page, not the V4 DS4.md one):
-#   --ds4-prefill dense   the V4.1 batched prefill. The default `exact` walks
-#                         the prompt token by token, and the V4-only modes are
-#                         REFUSED for V4.1: `sparse`, --ds4-fused-decode,
-#                         --ds4-fused-verify-f16-kv, layer split and --mmproj
-#                         all fail validate_model_features at load.
-#   --chunk 4096          the chunk the V4.1 dense-prefill numbers were taken
-#                         at; the runtime caps it to what the device holds.
+#   --ds4-prefill exact   THE ONLY prefill this placement can run. Any
+#                         approximate mode (dense, sparse) makes
+#                         DeepSeek4Backend::requires_monolithic_model() true,
+#                         and a monolithic load asks ggml for the whole 187 GiB
+#                         expert set as ONE device-0 buffer — measured
+#                         2026-09-26: "allocating 191932.25 MiB on device 0:
+#                         cudaMalloc failed: out of memory", then
+#                         "monolithic HIP load required for dense prefill".
+#                         DS41.md's dense-prefill section measures that mode
+#                         where the experts fit (in-process owners); on a
+#                         32 GiB target it cannot. exact feeds the prompt token
+#                         by token, which is what the hybrid tier streams for.
+#   --chunk 1024          DS41.md's cold-expert chunk. The runtime caps the
+#                         chunk to what fits after headroom regardless.
 #   --max-ctx 131072      the V4.1 default window. The MLA compressed caches
 #                         are F16 by design and stay small; --cache-type-k/v
 #                         are ignored by the DeepSeek4 backend, so they are
@@ -68,7 +75,7 @@ exec "$BIN" "$MODEL" \
     --model-name frank-primary \
     --target-device hip:0 \
     --max-ctx 131072 \
-    --chunk 4096 \
-    --ds4-prefill dense \
+    --chunk 1024 \
+    --ds4-prefill exact \
     --prefix-cache-slots 0 \
     --prefill-cache-slots 0